Loading…
This event has ended. Visit the official site or create your own event on Sched.
THE BIG FESTIVAL ABOUT SMALL CITIES
Tom Tom champions civic innovation, creativity, and entrepreneurship in America’s hometowns.

[Back to Tom Tom Festival]

Log in to bookmark your favorites and sync them to your phone or calendar.

Summit: Machine Learning [clear filter]
Thursday, April 11
 

7:00am EDT

Applied Machine Learning Conference: Check-In and Badge Pick-Up
You may also check in and pick up your badge in advance of the day of the conference. Please see our full week's box office hours here.

Thursday April 11, 2019 7:00am - 8:00am EDT
Violet Crown 200 W Main St, Charlottesville, VA 22902, USA

8:00am EDT

Applied Machine Learning Conference: Networking Coffee
Networking Coffee for the Applied Machine Learning Conference Guests, Speakers, and Exhibitors.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.


Thursday April 11, 2019 8:00am - 9:00am EDT
The Jefferson Theater 110 E. Main Street, Charlottesville VA 22902, USA

8:30am EDT

Applied Machine Learning Conference
The Best Boutique Machine Learning Conference on the East Coast
The Applied Machine Learning Conference has sold out for two years running and continues to generate excitement with its focus on applied science and practitioner-driven content. This premier, day-long event features a who’s who of researchers, entrepreneurs, and writers, as well as numerous opportunities for networking and recruitment at mixers, power lunches, and afterparties, all on Charlottesville’s picturesque Downtown Mall.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Joaquín Alori

Joaquín Alori

Research Engineer, Tryolabs
Joaquin Alori is a Research Engineer at Tryolabs, where he works on object tracking, pose estimation, and person re-id problems. Prior to joining Tryolabs he worked at ABB Uruguay as a Control Systems Engineer. He holds a BS in Manufacturing Engineering from Universidad de Montev... Read More →
avatar for Will Badart

Will Badart

Machine Learning Engineer, Booz Allen Hamilton
Will is a web developer turned software engineer turned data scientist at Booz Allen Hamilton. At Booz Allen, Will designs and builds novel, AI-driven cyber defenses and systems to deliver them. Will has a passion for design, vim, martial arts, and open source software.
avatar for Derek Bivona

Derek Bivona

PhD Candidate, Department of Biomedical Engineering, University of Virginia
Derek is a third-year PhD candidate in the Department of Biomedical Engineering at the University of Virginia. As a member of the Cardiac Biomechanics Group, he develops computer models to study heart growth and remodeling in response to both disease and therapy. Derek utilizes machine... Read More →
avatar for Carlos Blancarte

Carlos Blancarte

Data Scientist, Elder Research
Carlos Blancarte is drawn to analytics for its power to capture complex relationships and influence decision making. Previously, Carlos was lead statistician for a marketing research firm where he engaged in every stage of the project lifecycle from collecting, cleaning and analyzing... Read More →
avatar for Ben Bland

Ben Bland

Student, James Madison University
Ben Bland is a senior ISAT student from James Madison University, with a dual concentration in Information Knowledge Management and Energy. He is currently working on a capstone project using TensorFlow to train a small autonomous vehicle.
avatar for Adam Blum

Adam Blum

CEO, Deep Learn
CEO/CTO of several technology startups, adjunct professor at CMU and UC Berkeley, author of Neural Networks in C++, several patents in machine learning and related disciplines
avatar for Drew Bollinger

Drew Bollinger

Developer, Development Seed
Drew is a developer and data analyst at Development Seed. He has rich experience running advanced analysis and machine learning algorithms on large geospatial data sets. He is passionate about using powerful analysis and visualization techniques to promote social change. He is a firm... Read More →
avatar for Tom Brock

Tom Brock

CEO, ConvergentAI
Tom brings over 30 years experience in software and analytics.  He has had roles ranging from COO, CIO, GM and Strategy, spanning from industrial automation to healthcare analytics.  He has BS degree in Electrical Engineering from Georgia Tech, is a graduate of GE’s management... Read More →
avatar for Taylor Brown

Taylor Brown

Lecturer of Statistics, University of Virginia
Broadly interested in Bayesian statistics, time series, and computation.
TC

Tatyana Casino

Platform Software Engineer, WillowTree
Tatyana Casino is a software engineer at WillowTree, a mobile innovation agency. Tatyana has been building mobile apps for a variety of leading brands and clients. She has been developing for Android for 5 years, has done cross-platform development with Xamarin and worked on native... Read More →
avatar for Martin Chobanyan

Martin Chobanyan

Data Scientist, Commonwealth Computer Research, Inc. (CCRi)
Martin is a data scientist at Commonwealth Computer Research. His most recent work involves using computer vision and deep learning to localize targeted behaviors from maritime vessel trajectory data. He recently graduated from the University of Virginia with a bachelors in mathematical... Read More →
avatar for Nate Day

Nate Day

Data Scientist, HemoShear Therapeutics
Nathan builds analysis pipelines for drug discovery data. He utilizes Shiny applications and SQL databases to give researchers tools to explore their own experimental results. For fun Nathan practices yoga, plays squash, and helps on civic data projects. He's been living in Belmont... Read More →
avatar for Kimberly Deas

Kimberly Deas

Health Data Scientist, Rutgers University
Kimberly is a Health Data Scientist Consultant who works with for and non-profit organizations, academic institutions, and government agencies, providing statistical and data analytical support to their programs. Formerly educated in Chemistry and Pharmacology at the University of... Read More →
avatar for Pierre DeBois

Pierre DeBois

Founder / CEO, Zimana
Pierre DeBois is the founder and CEO of Zimana, an analytics services that help organizations achieve profitability improvements in marketing, Web development, and within their business operations. Zimana has provided services for businesses from many industries.Pierre has provided... Read More →
avatar for Ryan Duve

Ryan Duve

Using Google's BERT to Ask Financial Documents Questions, S&P Global
Ryan holds a PhD in physics from the University of Virginia, where his research focused on optical quantum computing, graphene synthesis and cryonuclear physics. His first exposure to data science was while working at Thomas Jefferson National Laboratory and Duke University, where... Read More →
avatar for Chris Eichelberger

Chris Eichelberger

Senior Software Developer / Data Scientist, CCRi
Chris is a long-time liberal arts and sciences advocate hiding behind a STEM career, so he talks funny, dresses worse, and is fond of the Oxford comma. In consideration of these faults, he has spent much of his adult life trying to divest of prescriptivism, which has unfortunate side... Read More →
avatar for Daniel Emaasit

Daniel Emaasit

Data Scientist, Haystax
I am a Data Scientist at Haystax in Washington, D.C. My interests involve developing principled probabilistic models for problems where training data are scarce by leveraging knowledge from subject-matter experts and context information. In particular, I am interested in flexible... Read More →
avatar for Andrew Fast

Andrew Fast

Chief Data Scientist, CounterFlow AI, Inc
Andrew Fast is the Chief Data Scientist and co-founder of CounterFlow AI, where he leads the implementation of streaming machine learning algorithms on CounterFlow AI's ThreatEye cloud-native analytics platform for Encrypted Traffic Analysis. Previously, Dr. Fast served as the Chief... Read More →
avatar for Kashaun Finch

Kashaun Finch

Student, James Madison University
I’m Kashuan Finch, a senior ISAT Major, with a concentration in Telecommunications, Networking and Security, and Robotics Minor at James Madison Univerisity. My interests in work and research are in applied machine learning, IT technology, software-defined devices, sustainable energy... Read More →
avatar for Miriam Friedel

Miriam Friedel

Director of Data Science, Skafos.ai
Dr. Miriam Friedel has spent over fifteen years in scientific and technical fields spanning theoretical physics, software engineering, transportation, neuroscience, and machine learning. She currently leads the data science team at Skafos.ai (formerly Metis Machine) in Charlottesville... Read More →
avatar for William Goodrum

William Goodrum

Data Scientist, Elder Research, Inc.
Will Goodrum is a Data Scientist with Elder Research, Inc., a Data Science and Machine Learning consultancy based in Charlottesville, VA. During his time with ERI, Will has provided Data Science and strategy consulting services to clients in industries like maritime risk, logistics... Read More →
avatar for John Harris

John Harris

Data Scientist, Cogit Analytics
John is the chief data scientist for Cogit Analytics. He has extensive experience designing and building advanced analytics, machine learning, and other quantitative solutions in supply chain, finance, and healthcare.
avatar for Henry Harris

Henry Harris

Student, University of Virginia
Henry is a fourth-year student at the University of Virginia studying Computer Science and Economics. He spent this past summer as an intern with Elder Research’s Data Science team here in Charlottesville, working primarily on time series predictive software. Outside of data science... Read More →
avatar for Elizabeth Harrison

Elizabeth Harrison

Dual Degree Candidate, University of Virginia School of Medicine & School of Data Science
Elizabeth Harrison is a fourth year medical student at the University of Virginia School of Medicine and a recent graduate of UVA's Master of Science in Data Science degree program. She is currently working on a number of clinical research projects involving the application of data... Read More →
avatar for Matthew Hendrickson

Matthew Hendrickson

Principal Data Analyst, HelioCampus
Matthew is passionate about data, analytics, and research. Since completing his Doctorate in Law and Policy, with a focus on Data Privacy, he muses over the legal implications of big data. However, he must balance those concerns against the tremendous benefit of amassing and analyzing... Read More →
avatar for Sakshi Jawarani

Sakshi Jawarani

Graduate Student, University of Virginia, Data Science Institute
I'm currently pursuing a Graduate degree in Data Science at the University Of Virginia. I look forward to using the technical competencies gained through my program and apply it to real world business problems. I believe like the human brain, data too has limitless potential and as... Read More →
avatar for Brad Johnson

Brad Johnson

Data Scientist, TwinThread
With a background in startup tech and consulting, Brad’s career in machine learning and industrial IoT kicked into high gear with a project helping Hershey produce Twizzlers more efficiently. As lead Data Scientist at TwinThread, Brad enjoys working on applying (and explaining... Read More →
avatar for Mo Johnson

Mo Johnson

Community Lead, Data for Democracy
Maureen (Mo) Johnson has a background in public health, anthropology and social science research. She has worked and studied in Europe, North and South America, and Asia. Because of these diverse cultural and linguistic experiences, she became interested in digital cooperation, data... Read More →
avatar for Neeyanth Kopparapu

Neeyanth Kopparapu

Student, Thomas Jefferson High School for Science and Technology
Neeyanth Kopparapu is a High School Junior at Thomas Jefferson High School in Alexandria, VA. As a student, he is interested in mathematics, computer science, and physics. He is especially interested in developing computer science (specifically artificial intelligence) models to help... Read More →
avatar for Anton Korinek

Anton Korinek

Associate Professor, UVA Economics and Darden
Anton Korinek is an Associate Professor at the Department of Economics and the Darden School of Business at the University of Virginia. His current research focuses on the implications of rapid progress in Artificial Intelligence for inequality, work, and for the future of humanity... Read More →
avatar for Olivera Kotevska

Olivera Kotevska

Postdoctoral researcher, Oak Ridge National Laboratory
Olivera Kotevska is a postdoctoral researcher in Computer Science and Mathematics at Oak Ridge National Laboratory (ORNL), Tennessee, USA. Olivera received her Ph.D. degree in Computer Science from the University of Grenoble Alpes, Grenoble, France in 2018. Before joining ORNL, she... Read More →
avatar for Stephen Levin

Stephen Levin

Special Projects, Zapier
Stephen does Special Projects for the CEO at Zapier, a workflow automation tool used by over 3 million people to connect the work apps they use every day. He uses data to help inform decisions in product, strategy, marketing, and operations. He also founded Think Analytically, where... Read More →
avatar for Steven Lott

Steven Lott

Master Software Engineer, Capital One
Steve has been developing software since computers were large, expensive, and rare. He's written several books on Python, published by Packt.
avatar for Malcolm MacLachlan

Malcolm MacLachlan

Software Engineer, CCRi
Malcolm is a software engineer at CCRi. He has experience building web and mobile applications for data analytics. He is interested in the intersection of music and technology and co-owns a record label based out of Detroit, MI.
avatar for Sean Mullane

Sean Mullane

Data Scientist, UVA Health System
Sean is currently working as a data scientist in the UVA Health System while completing a Master's degree at the UVA Data Science Institute, where he is researching the applications of machine learning to protein structure prediction. He has lived in Charlottesville, VA since graduating... Read More →
avatar for Sarah Olson

Sarah Olson

Data Scientist, Booz Allen Hamilton
Sarah Olson is a Data Scientist at Booz Allen Hamilton, with current focus areas in cyber security, machine learning models, and natural language processing. Her projects at the company have supported a variety of her interests, ranging from developing models to detect credential... Read More →
avatar for Esther Onega

Esther Onega

Senior Project Manager for Alderman Renovation, University of Virginia Library
Ms. Onega has worked at the UVA Library since 1997, in a variety of librarian and project management positions. She received her MLS from University of Maryland and her Project Management certificate from the University of Virginia. Her strengths include a thorough knowledge of the... Read More →
avatar for Bill Panak

Bill Panak

Vice President, Data Science, Halo, the Supply Chain Intelligence Company
As VP of Data Science, my role is to create proprietary supply chain algorithms and foundational data workflow assets, and to productize and monetizing these assets on behalf of our customers. To do this, I draw on my experiences as a PhD “quant” and 25 years of work in psychology... Read More →
avatar for Murugesan Ramakrishnan

Murugesan Ramakrishnan

Graduate Student, Data Science Institute, University of Virginia
Murugesan is a current Graduate student at the Data Science Institute, University of Virginia. His research interest lies in solving problems in Natural Language Processing and Computer Vision using Deep Learning techniques, He also has a considerable experience in consulting solving... Read More →
avatar for Rakesh Ravi

Rakesh Ravi

Graduate Student, University of Virginia, Data Science Institute
Rakesh is a graduate student in Data Science at the University of Virginia and has substantial industry experience in complex data analysis, text mining, data visualization and deploying machine learning models on real-world data. He is passionate about finding machine learning applications... Read More →
avatar for Charu Rawat

Charu Rawat

Graduate Student, University of Virginia
Charu is currently a graduate student at UVA pursuing her Masters in Data Science at the Data Science Institute. Prior to this, she earned a bachelor's degree in Mathematics and worked at The D.E. Shaw Group for 3 years leveraging alternative data for investment decisions. Her research... Read More →
avatar for Austin Rochford

Austin Rochford

Chief Data Scientist, Monetate
Austin Rochford is Principal Data Scientist and Director of Monetate Labs. He is a founding member of Monetate Labs, where he does research and development for machine learning-driven marketing products. He is a recovering mathematician, a passionate Bayesian, and a PyMC3 developer... Read More →
avatar for Erin Ryan

Erin Ryan

Astronomer, SETI Institute
Erin Lee Ryan is an asteroid that can be found approximately 4 AU from the Sun. It's human namesake can be mostly frequently found in the Charlottesville area trying to do science on some form of imagery. She holds a bachelors in astronomy from the University of Arizona and a PhD... Read More →
avatar for Arnab Sarkar

Arnab Sarkar

Student, University of Virginia, Data Science Institute
Budding Data Scientist, with more than 3 years of experience in Oracle PL/SQL, Oracle E-Business Suite ERP platform, Oracle Demantra and Talend Data Integration tool. Currently pursuing a Master's degree in the field of Data Science and looking to expand my knowledge in both the statistical... Read More →
avatar for Aman Shrivastava

Aman Shrivastava

Student, University of Virginia
I am a Data Science masters student at the Data Science Institute, University of Virginia. With an eclectic background through my education and engagements with organizations in different domains, I am passionate about finding interdisciplinary applications of data science, particularly... Read More →
avatar for Sameer Singh

Sameer Singh

Graduate Student, Data Science Institute, University of Virginia
Sameer Singh is currently pursuing M.S. in Data Science at the University of Virginia.He has considerable work experience in data analytics and consulting. At ZS Associates, he provided analytics based sales and marketing solutions such as promotion response modeling, marketing mix... Read More →
avatar for Varshini Sriram

Varshini Sriram

Graduate Student, Data Science Institute, University of Virginia
Varshini is currently a graduate student at the University of Virginia pursuing her Masters in Data Science. Her research interests include Natural Language Processing and Computer Vision. She is currently working on the Collective Biographies of Women project at UVA where the goal... Read More →
avatar for Anthony Teate

Anthony Teate

Professor, James Madison University
Dr. Anthony A. Teate is a tenured Professor in the School of Integrated Sciences located in the College of Integrated Science and Engineering at James Madison University, where he is also the Director of the Data Science and Applied Machine Learning Laboratory. His current areas of... Read More →
avatar for Renee Teate

Renee Teate

Data Scientist, HelioCampus
Renee M. P. Teate is a Data Scientist at HelioCampus, and the creator of the Becoming a Data Scientist Podcast and @becomingdatasci twitter account. She has worked with data for her entire career - designing relational databases, creating reports and analyses, and most recently developing... Read More →
avatar for Andrew Therriault

Andrew Therriault

Manager, Infrastructure Data Science, Facebook
Andrew Therriault has spent the past decade building and leading data science programs for organizations across the political, nonprofit, government, and technology sectors. He founded the Democratic National Committee’s data science team in 2014 and was appointed the City of Boston’s... Read More →
avatar for Samantha Toet

Samantha Toet

Partner Marketing, RStudio
Samantha Toet is a C'ville native, UVA alum, and the Founder of R-Ladies Charlottesville, a local chapter of a worldwide organization dedicated to promoting gender diversity in the R and data science community. She currently works as partner marketing specialist for RStudio, the company... Read More →
avatar for Alli Torban

Alli Torban

Data Visualization Designer, American Enterprise Institute
Alli Torban is a Data Visualization Designer for the American Enterprise Institute in Washington, D.C. where she transforms public policy research into meaningful graphics for decision-makers and the general public. She’s passionate about revealing the patterns and insights hidden... Read More →
avatar for Sri Vaishnavi Vemulapalli

Sri Vaishnavi Vemulapalli

Graduate Student, Data Science Institute, University of Virginia
Sri is a Graduate Student pursuing her Masters in Data Science at the Data Science Institute, University of Virginia. She has a background in Information Systems and experience as a Software Development Engineer. Her areas of interest are Natural Language Processing and Visual Re... Read More →
avatar for Tianlu Wang

Tianlu Wang

Graduate Student, University of Virginia, Department of Computer Science
Tianlu Wang is a Ph.D. student at the Department of Computer Science at the University of Virginia. She has been working with Prof. Vicente Ordóñez Román since Fall 2016. Her research focus lies at the intersection of computer vision and natural language processing. More recently... Read More →
avatar for Courtney Whalen

Courtney Whalen

Data Scientist, Astraea, Inc.
Courtney Whalen is a data scientist at Astraea, Inc., where she is using satellite imagery and machine learning techniques to answer complex global questions. She has been working as a data scientist for 5 years and has experience developing machine learning models across several... Read More →
avatar for Joy Williams

Joy Williams

JMU Undergraduate Student, James Madison University, ISAT
Joy Williams is a senior at James Madison University and will graduate with an Integrated Science and Technology degree with a concentration in Information and Knowledge Management. She is passionate about finding new ways to integrate machine learning in different softwares to help... Read More →
avatar for Vida Williams

Vida Williams

Data Solutions Lead/Innovator in Residence, Singlestone Consulting/VCU DaVinci Center
Vida is an innovation advocate who is determined that innovation not leave humanity behind. She utilizes her experience as a data scientist to drive social and economic change in communities. A promising start as a tech writer spurred a nearly 20 year career with data, technology... Read More →
avatar for Ken Zamkow

Ken Zamkow

General Manager for United States, run:ai
Ken leads the US activity for run:ai, a startup that helps deep learning engineers and data scientists to significantly speed up the training of their neural network models, while reducing compute costs and workflow complexities.Previously, Ken was the Founder and CEO of SportsGuru... Read More →
avatar for Michael Zelenetz

Michael Zelenetz

Analytics Project Lead, NewYork-Presbyterian
Michael is a paramedic turned data scientist. He works on the analytics team at NewYork-Presbyterian and is passionate about using data to improve healthcare.

Sponsors

Thursday April 11, 2019 8:30am - 6:00pm EDT
Violet Crown 200 W Main St, Charlottesville, VA 22902, USA

9:00am EDT

Data is Rarely Neutral: Bias in the Practice of Data
You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Vida Williams

Vida Williams

Data Solutions Lead/Innovator in Residence, Singlestone Consulting/VCU DaVinci Center
Vida is an innovation advocate who is determined that innovation not leave humanity behind. She utilizes her experience as a data scientist to drive social and economic change in communities. A promising start as a tech writer spurred a nearly 20 year career with data, technology... Read More →

Sponsors

Thursday April 11, 2019 9:00am - 10:00am EDT
The Jefferson Theater 110 E. Main Street, Charlottesville VA 22902, USA

10:15am EDT

Social Media Sentiment Analysis with R - Bot or Not?
There has been an upsurge in conference twitter bots arising to promote conferences and I plan on investigating the efficacy of these further. In this session I will explore interfacing with the Twitter API, perform multiple types of sentiment analysis on Twitter content, and demonstrate how machine learning can predict whether an account is a bot and what that bot or person might say through wordwalking. I will primarily focus on tweets pertaining to technology conferences, and will include @TomTom and #AMLCville hashtags as examples.


You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Samantha Toet

Samantha Toet

Partner Marketing, RStudio
Samantha Toet is a C'ville native, UVA alum, and the Founder of R-Ladies Charlottesville, a local chapter of a worldwide organization dedicated to promoting gender diversity in the R and data science community. She currently works as partner marketing specialist for RStudio, the company... Read More →

Sponsors

Thursday April 11, 2019 10:15am - 10:30am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:15am EDT

Auto-What? A Taxonomy of Automated Machine Learning
AutoML is one of the most robust areas of innovation in applied machine learning. New products in this space from the likes of Google and new AI-focused startups are appearing constantly, all of which promise to make machine learning accessible to the masses without the need for trained data scientists. At its base, AutoML involves some selection and configuration of machine learning algorithms. However, each product seems to have its own take of what parts of the machine learning process to automate and how they do it.   

We believe the industry could use a taxonomy of capabilities of AutoML tools. These capabilities include the following: choosing algorithms, setting hyperparameters, controlling model search and training time, cross-validation, data preprocessing, and feature creation. While Gartner has yet to offer a Magic Quadrant for AutoML, perhaps this overview can help inform a future effort as the automated machine learning sector matures.

This talk will cover each of these topic and discuss tools and techniques available in each area. 


You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Adam Blum

Adam Blum

CEO, Deep Learn
CEO/CTO of several technology startups, adjunct professor at CMU and UC Berkeley, author of Neural Networks in C++, several patents in machine learning and related disciplines

Sponsors

Thursday April 11, 2019 10:15am - 10:45am EDT
Violet Crown: Theater 2

10:15am EDT

Don't Stop Disbelieving
This session is meant to summarize hard lessons learned from decades of data processing, data analysis, data mining, and recently data science.  We discuss the subtleties of GIGO -- Garbage In, Garbage Out -- and how this lurks within every data task we undertake, from deep learning to service orchestration, in ways that can be difficult to recognize.  Real-life case studies highlight the various ways in which well-meaning data scientists and their clients can do harm if we do not practice our core skepticism.  These personal lessons learned and supporting examples are organized into three themes:
  • the data is not the thing
    • a medical model to bolster physician exposure to rare cases:  mistaking choices we made for choices we should have made
  • the model is not the thing
    • predicting fraud to generalize a curated set of rules:  mistaking machine learning for human learning
  • the data scientist is not the thing
    • a financial-services model of customer satisfaction:  mistaking modeller integrity for solution integrity
The synthesis / take-home message -- what the thing IS -- is to recognize modeling as metaphor:  Every instance is imperfect, but some can be useful.  The right approach is to iterate on not only modeling and development but on communication and cross-expertise vetting so as to constrain and characterize the imperfections.


You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Chris Eichelberger

Chris Eichelberger

Senior Software Developer / Data Scientist, CCRi
Chris is a long-time liberal arts and sciences advocate hiding behind a STEM career, so he talks funny, dresses worse, and is fond of the Oxford comma. In consideration of these faults, he has spent much of his adult life trying to divest of prescriptivism, which has unfortunate side... Read More →

Sponsors

Thursday April 11, 2019 10:15am - 10:45am EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

10:20am EDT

The Hamiltonian Monte Carlo Revolution is Open Source: Probabilistic Programming with PyMC3
In the last ten years, there have been a number of advancements in the study of Hamiltonian Monte Carlo and variational inference algorithms that have enabled effective Bayesian statistical computation for much more complicated models than were previously feasible. These algorithmic advancements have been accompanied by a number of open source probabilistic programming packages that make them accessible to the general engineering, statistics, and data science communities. PyMC3 is one such package written in Python and supported by NumFOCUS. This talk will give an introduction to probabilistic programming with PyMC3, with a particular emphasis on the how open source probabilistic programming makes Bayesian inference algorithms near the frontier of academic research accessible to a wide audience.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Austin Rochford

Austin Rochford

Chief Data Scientist, Monetate
Austin Rochford is Principal Data Scientist and Director of Monetate Labs. He is a founding member of Monetate Labs, where he does research and development for machine learning-driven marketing products. He is a recovering mathematician, a passionate Bayesian, and a PyMC3 developer... Read More →

Sponsors

Thursday April 11, 2019 10:20am - 10:50am EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

10:30am EDT

Featured Student Research Lightning Talks: Collective Biographies of Women - A Deep Learning Approach to Paragraph Annotation
The Collective Biographies of Women Project (CBW) investigates cultural representations of women through a large corpus of British and American biographical texts from the nineteenth and twentieth centuries. The texts belong to the collective biography genre, with volumes containing several chapter-length biographies of different women organized around a common theme. The CBW project is supported by Dr. Alison Booth, Director of Scholars Lab at the University of Virginia
CBW seeks to annotate these biographies at the paragraph level using a controlled vocabulary to label each paragraph according to a set of literary-critical dimensions. These dimensions are defined in a controlled vocabulary known as BESS, Biographical Elements and Structure Schema. The BESS vocabulary consists of tags such as - Stage Of life, Persona, Event, Topos, Discourse. The BESS tag Event has labels such as marriage, birth, death. Ultimately, the goal of the project is to develop a complete annotated corpus drawn from 1,270 known books, comprising around 13,000 chapters of about 8,000 women. 
Each paragraph in the biography will be classified with its corresponding BESS annotation. Textual features like Bag of Words, TF-IDFs and linguistic features like semantic and syntactic parameters among others will be used as the model features. Our initial approach to classification will be using a variety of Machine Learning models like Logistic Regression, Tree-Based Models and SVMs. The results of the above model will be considered as our baseline result for our deep learning results.
With the baseline scores from Machine Learning models, the biographiles are annotated using a Recurrent Neural Network approach. Multi-layered bidirectional LSTM based model will be used to understand the context and theme of a paragraph and identify the corresponding BESS annotation. Every word will be initiated with their predefined GloVe embeddings which will further trained to get their meaning aligned with the context of biographies. Different architectures with be tried and tested before selecting the best one suited to this use case. Especially because biographies have not been worked upon a lot in Natural Language Processing, it should be a challenging task arriving at an optimal architecture.
The next objective is to find common events associated with a women in each biography. This is done by drawing parallels with Market Basket Analysis. Just like in Market Basket Analysis where there is some % of probability of the presence of an item in a cart given another item is present, here a cart is represented by a paragraph and the items are words in a paragraph. So, all words (non-trivial word) with higher probability associated with each woman is identified. This is useful in getting a quick gist/summary of the life events of a woman. Thus, with the above objectives, we identify what each paragraph in a biography is talking about and at the same time what are the important life events associated with every woman.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Sakshi Jawarani

Sakshi Jawarani

Graduate Student, University of Virginia, Data Science Institute
I'm currently pursuing a Graduate degree in Data Science at the University Of Virginia. I look forward to using the technical competencies gained through my program and apply it to real world business problems. I believe like the human brain, data too has limitless potential and as... Read More →
avatar for Murugesan Ramakrishnan

Murugesan Ramakrishnan

Graduate Student, Data Science Institute, University of Virginia
Murugesan is a current Graduate student at the Data Science Institute, University of Virginia. His research interest lies in solving problems in Natural Language Processing and Computer Vision using Deep Learning techniques, He also has a considerable experience in consulting solving... Read More →
avatar for Varshini Sriram

Varshini Sriram

Graduate Student, Data Science Institute, University of Virginia
Varshini is currently a graduate student at the University of Virginia pursuing her Masters in Data Science. Her research interests include Natural Language Processing and Computer Vision. She is currently working on the Collective Biographies of Women project at UVA where the goal... Read More →

Sponsors

Thursday April 11, 2019 10:30am - 11:05am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:30am EDT

Featured Student Research Lightning Talks: Cyber Harassment Detection and Prediction of User Blocks in Wikipedia
The advent of the Internet can be easily heralded as oneof the key events which led to the “Information age” as it is colloquially known. Sharing of thoughts, ideas and opinions reached new heights when people were able to engage in meaningful debates through online forums. However, a darker aspect to this medium – online harassment, has become became rampant in these communities. The Wikipedia usercommunity is no stranger tothis phenomenon.As of January 2019, Wikipedia has 35 million users and on average 250k users register every month. Also, as per the Wikipedia Community Engagement Insights 2018 report - 68% of the respondents reported having experienced harassment at some point in the past and as a result about22% of Wikipedians reported a decrease in their contribution levels. To combat harassment, currently Wikipedia has an organic, human-driven process in place, where cases of abuse reported are evaluated and enacted upon by Wikipedia administrators.Butrelying on human evaluation works in someways but it is not a solution which scales with the growth of Wikipedia, as there were ~170k user blocks in 2018 alone. 
Our goal is to develop a data-driven approach in combating cyber harassment that will address a variety of issues that are otherwise faced by the human driven process, from errors and bias in human judgement to efficiently evaluating a larger magnitude of cases. By analyzing user activity in form of editing behavior and discussions, we will be able to predict users who are at risk of getting blocked in the future. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Charu Rawat

Charu Rawat

Graduate Student, University of Virginia
Charu is currently a graduate student at UVA pursuing her Masters in Data Science at the Data Science Institute. Prior to this, she earned a bachelor's degree in Mathematics and worked at The D.E. Shaw Group for 3 years leveraging alternative data for investment decisions. Her research... Read More →
avatar for Arnab Sarkar

Arnab Sarkar

Student, University of Virginia, Data Science Institute
Budding Data Scientist, with more than 3 years of experience in Oracle PL/SQL, Oracle E-Business Suite ERP platform, Oracle Demantra and Talend Data Integration tool. Currently pursuing a Master's degree in the field of Data Science and looking to expand my knowledge in both the statistical... Read More →
avatar for Sameer Singh

Sameer Singh

Graduate Student, Data Science Institute, University of Virginia
Sameer Singh is currently pursuing M.S. in Data Science at the University of Virginia.He has considerable work experience in data analytics and consulting. At ZS Associates, he provided analytics based sales and marketing solutions such as promotion response modeling, marketing mix... Read More →

Sponsors

Thursday April 11, 2019 10:30am - 11:05am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:30am EDT

Featured Student Research Lightning Talks: derML: A Machine Learning, Image Recognition Mobile Application That Assists in Skin Cancer Detection
Each year in the United States, over 5.4 million cases of nonmelanoma skin cancer are treated. Fortunately, skin cancer is the easiest cancer to cure if diagnosed and treated early; however, early detection is not always easy. The aim of this project was to develop a solution for early skin cancer detection that is readily available to 70%-80% of smart phones users. derML is a mobile application developed for the Android platform that uses machine learning and image recognition technology with Google’s TensorFlow framework to find patterns in pictures of skin moles, lesions, or other anomalies. The intent is for the algorithms to accurately predict if a given image of a skin anomaly is cancerous or benign and deliver that information to the user through an easy-to-use app.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Joy Williams

Joy Williams

JMU Undergraduate Student, James Madison University, ISAT
Joy Williams is a senior at James Madison University and will graduate with an Integrated Science and Technology degree with a concentration in Information and Knowledge Management. She is passionate about finding new ways to integrate machine learning in different softwares to help... Read More →

Sponsors

Thursday April 11, 2019 10:30am - 11:05am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:30am EDT

Featured Student Research Lightning Talks: Detection of Malicious Cyber Activity at University of Virginia using Machine Learning
In the last six months of 2018, there were over 181 million ransomware attacks, marking a 229% increase from the same time frame in 2017. While most corporations are making progress in finding elegant solutions to counteract malware attacks, university networks remain vulnerable targets due to a lack of appropriate security mechanisms. In 2017, atleast 5 universities in the United States were victims of ransomware attacks. 
Constructing intrusion detection systems using machine learning is an area that has enticed researchers for a long time. Data acquisition is one of the biggest challenges in building such a system. Data on malware attacks is generally not made public by organizations due to privacy concerns. As a result, many of the cybersecurity solutions that have been built thus far are based on attack simulations generated by cybersecurity experts. 
In our project, we are utilizing the connection logs acquired from the cybersecurity team at the University of Virginia. In order to label the connection logs, we collect data on malicious attacks using low interaction honeypots, systems designed to appear as vulnerable targets in order to lure attackers, on to sub networks at the University of Virginia. 
One issue that plagues intrusion detection systems is class imbalance which occurs due to the overwhelming majority of benign traffic that exists across networks. In the field of cybersecurity, the cost of misclassifying minority class samples, false positives, is much higher the cost of misclassifying majority class samples. We remedy the issue of class imbalance using SVM-SMOTE (Support Vector Machines - Synthetic Minority Over Sampling Technique) to create synthetic samples which will balance the class labels in the dataset. SVM-SMOTE is an oversampling technique that generates new minority class instances near borderlines with SVMs so as to help establish boundaries between different classes. 
Our hypothesis is that the approach of detecting malicious activity using honeypots, which has been proven to work on partially simulated datasets, will effectively predict malicious attacks on active network data. In our project, we label the university network connections as ‘benign’ or ‘malicious’ using data captured by the honeypots. We treat the labelled data with SVM-SMOTE to resolve class imbalance and build a machine learning classifier. We use deep learning and ensemble learning on the dataset to further improve performance of the model. The proposed system would improve the overall accuracy of detecting malicious activity and minimize false positives. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Rakesh Ravi

Rakesh Ravi

Graduate Student, University of Virginia, Data Science Institute
Rakesh is a graduate student in Data Science at the University of Virginia and has substantial industry experience in complex data analysis, text mining, data visualization and deploying machine learning models on real-world data. He is passionate about finding machine learning applications... Read More →

Sponsors

Thursday April 11, 2019 10:30am - 11:05am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:30am EDT

Featured Student Research Lightning Talks: Using TensorFlow Machine Learning to Develop and Train a Small-Scale Autonomous Vehicle
Autonomous features are slowly being introduced into recent car models. Our team is aiming to create our own autonomous robotic car using a Raspberry Pi, Python, the Google Vision API, and TensorFlow. The first stage of the project focused on allowing the car to recognize logos, and having it “speak” what it saw through a speaker. The second stage of the project focuses on creating our own algorithm in TensorFlow and embedding the algorithm onto the Raspberry Pi, allowing it to recognize traffic signs and navigate accordingly. The car will also be able to upload its algorithms to a cloud environment, where other cars with lower-scoring accuracy models will be able to download the more accurate model. This models how cars could be maintained in the future by downloading updates from the manufacturer.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Ben Bland

Ben Bland

Student, James Madison University
Ben Bland is a senior ISAT student from James Madison University, with a dual concentration in Information Knowledge Management and Energy. He is currently working on a capstone project using TensorFlow to train a small autonomous vehicle.
avatar for Kashaun Finch

Kashaun Finch

Student, James Madison University
I’m Kashuan Finch, a senior ISAT Major, with a concentration in Telecommunications, Networking and Security, and Robotics Minor at James Madison Univerisity. My interests in work and research are in applied machine learning, IT technology, software-defined devices, sustainable energy... Read More →

Sponsors

Thursday April 11, 2019 10:30am - 11:05am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

10:50am EDT

A Deep Learning Approach to Meme Generation
Natural language is used in day to day life to evoke and convey thoughts, feelings, and emotions. One of the emotions commonly expressed through language is humor. It is a universal phenomenon that occurs in all languages and has a wide appeal.With the advent of social media platforms, new forms of creative expression such as memes and gifs have become really popular. 
Generating humor is challenging because it is not always direct. It can have different styles such as sarcasm, satire, irony etc. In the context of memes, the joke has to be expressed in a few words, usually 20 or less and support the background image. Hence, the syntax of the language used in memes is different and does not follow the conventional language structure. 
In this project, we introduce a model using encoder-decoder framework with attention mechanism to generate memes where the attention mechanism is applied on an abstract vector space representing the image and thematic linguistic representation of the meme. 
An attention based encoder decoder framework was implemented where the encoder extracts an abstract representation of the image from a pre-trained Resnet101 model while the decoder was composed a an LSTM network that generated the output word by word. The attention mechanism was incorporated to inspect and take into account the presence of certain objects that guide the process of generating any given word by focusing on a certain area of the image. 
To provide more context to the memes, in addition to the above architecture pre-trained GloVe embedded vectors were used as the initial weights for the input text. Unconventional words like 'bae' were pre-assigned with a random vector. All of these vectors were again trained to fine-tune their weights. This initialization approach assisted in faster convergence of embedding weight matrix. 
A descriptive representation of the meme was introduced in the encoder in order to better capture the sentiment and thematic structure of the meme. Keywords representing the sentiment of the meme were converted to GloVe embeddings and concatenated with the image vector. This encoding was passed to the attention mechanism so that it could generate words based on an abstract combination of the pictorial and thematic properties of the meme. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Murugesan Ramakrishnan

Murugesan Ramakrishnan

Graduate Student, Data Science Institute, University of Virginia
Murugesan is a current Graduate student at the Data Science Institute, University of Virginia. His research interest lies in solving problems in Natural Language Processing and Computer Vision using Deep Learning techniques, He also has a considerable experience in consulting solving... Read More →
avatar for Sri Vaishnavi Vemulapalli

Sri Vaishnavi Vemulapalli

Graduate Student, Data Science Institute, University of Virginia
Sri is a Graduate Student pursuing her Masters in Data Science at the Data Science Institute, University of Virginia. She has a background in Information Systems and experience as a Software Development Engineer. Her areas of interest are Natural Language Processing and Visual Re... Read More →

Sponsors

Thursday April 11, 2019 10:50am - 11:05am EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

10:50am EDT

Automated Time-Series Model Selection at Scale
In logistics, accurate forecasting of incoming demand is the first and most crucial step in a long value chain leading all the way down to getting a package through the last mile. Near term forecasts are necessary for resource balancing and shift staffing, with long-term forecasts instrumental in large-scale capital purchases and network modifications (“How many 747s do we need to buy this year, anyway?”). Across a network of more than 2000 sites, each with its own schedules and services, the number of forecasts and planning permutations begins to enter the millions. 
In this talk, we will walkthrough at a high-level the automated framework that we implemented in R and Spark for a global logistics company that produces over 35 million forecasts weekly. Planning the future, all without the click of a button! 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Carlos Blancarte

Carlos Blancarte

Data Scientist, Elder Research
Carlos Blancarte is drawn to analytics for its power to capture complex relationships and influence decision making. Previously, Carlos was lead statistician for a marketing research firm where he engaged in every stage of the project lifecycle from collecting, cleaning and analyzing... Read More →
avatar for William Goodrum

William Goodrum

Data Scientist, Elder Research, Inc.
Will Goodrum is a Data Scientist with Elder Research, Inc., a Data Science and Machine Learning consultancy based in Charlottesville, VA. During his time with ERI, Will has provided Data Science and strategy consulting services to clients in industries like maritime risk, logistics... Read More →
avatar for Henry Harris

Henry Harris

Student, University of Virginia
Henry is a fourth-year student at the University of Virginia studying Computer Science and Economics. He spent this past summer as an intern with Elder Research’s Data Science team here in Charlottesville, working primarily on time series predictive software. Outside of data science... Read More →

Sponsors

Thursday April 11, 2019 10:50am - 11:05am EDT
Violet Crown: Theater 2

10:50am EDT

Estimating Multivariate Stochastic Volatility Models with Particle MCMC
Factor Stochastic Volatility (FSV) models are useful for managing investment risk and constructing portfolios. They possess a latent low-dimensional random process to help explain a higher-dimensional vector of finacial returns. This hidden process can represent anything the investor deems pertinent
Despite being expressive models in this class are exceedingly difficult to estimate. Within a Bayesian framework Gibbs sampling is the most common approach yet this is only available for some models used along with certain priors. Variants of Metropolis-Hastings are theoretically justified however they do not mix well in practice.
We argue that Particle Markov chain Monte Carlo techniques a newer set of likehood-free MCMC algorithms are well-suited to this task. We describe the general principles of the algorithm strategies for parallelization and show some examples of estimating different models. We also demonstrate once these models are estimated their out-of-sample forecasting performance. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Taylor Brown

Taylor Brown

Lecturer of Statistics, University of Virginia
Broadly interested in Bayesian statistics, time series, and computation.

Sponsors

Thursday April 11, 2019 10:50am - 11:05am EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

11:15am EDT

Using Google's BERT to Ask Financial Documents Questions
In 2018, BERT changed the world of natural language processing.  This talk will introduce BERT by going through a specific, real-world application of it in the financial services industry.  S&P is hiring, so if this talk piques your interest please check out our AI engineering job openings.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Ryan Duve

Ryan Duve

Using Google's BERT to Ask Financial Documents Questions, S&P Global
Ryan holds a PhD in physics from the University of Virginia, where his research focused on optical quantum computing, graphene synthesis and cryonuclear physics. His first exposure to data science was while working at Thomas Jefferson National Laboratory and Duke University, where... Read More →

Sponsors

Thursday April 11, 2019 11:15am - 11:30am EDT
Violet Crown: Theater 2

11:15am EDT

"Becoming a Data Scientist" Live Podcast featuring Andrew Therriault
You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Moderators
avatar for Renee Teate

Renee Teate

Data Scientist, HelioCampus
Renee M. P. Teate is a Data Scientist at HelioCampus, and the creator of the Becoming a Data Scientist Podcast and @becomingdatasci twitter account. She has worked with data for her entire career - designing relational databases, creating reports and analyses, and most recently developing... Read More →

Speakers
avatar for Andrew Therriault

Andrew Therriault

Manager, Infrastructure Data Science, Facebook
Andrew Therriault has spent the past decade building and leading data science programs for organizations across the political, nonprofit, government, and technology sectors. He founded the Democratic National Committee’s data science team in 2014 and was appointed the City of Boston’s... Read More →

Sponsors

Thursday April 11, 2019 11:15am - 11:45am EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

11:15am EDT

Artificial Intelligence / Machine Learning in The Supply Chain
There is a very positive 10 year outlook for hiring and STEM innovation in the supply chain, and a growing entry-level STEM workforce seeking opportunity in applied data science.  These two forces, combined with the relative “newness” of university training programs focused on the supply chain, create a knowledge gap between the typical entry-level data scientist seeking employment and the knowledge and skills needed to succeed as a leader of the supply chain of the future.  The purpose of this talk is to close that gap, to help entry level and mid career “citizen scientists” understand these forces in supply chain innovation, and to generate conversations on how to match supply chains in the private and public sectors with data scientists who can lead in sustainable, socially responsible supply chain innovation.
We are surrounded by, interact with, and are dependent on a large set of highly complex supply chain networks.  These private sector and public sector network interact with each other, creating massive amounts of high value data assets, in an ecosystem that is primed for smart and socially responsible application of artificial intelligence and machine learning.  This talk focuses on how these supply chain networks has become so integral to day-to-day human activity in ways that the common person often overlooks, but that are fertile development opportunities for data scientists.  A brief history, current state-of-the-science, and 10 year vision of enhanced AI in the supply chain will be presented, followed by deeper illustration of 3 central machine learning use cases: enterprise-scale multivariate demand forecasting, human-computer interface enhancement, and IOT.  The presenter will describe algorithms with broad application in the supply chain, the method of productizing algorithms for commercial distribution, and the skill set needed for an entry level data scientist to move into this type of work.  

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Bill Panak

Bill Panak

Vice President, Data Science, Halo, the Supply Chain Intelligence Company
As VP of Data Science, my role is to create proprietary supply chain algorithms and foundational data workflow assets, and to productize and monetizing these assets on behalf of our customers. To do this, I draw on my experiences as a PhD “quant” and 25 years of work in psychology... Read More →

Sponsors

Thursday April 11, 2019 11:15am - 11:45am EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

11:15am EDT

Pymc-Learn: Practical Probabilistic Machine Learning in Python
Pymc-learn is a Python package providing a variety of state-of-the-art probabilistic models for supervised and unsupervised machine learning. It is inspired by scikit-learn and focuses on bringing probabilistic machine learning to non-specialists. It uses a general-purpose high-level language that mimics scikit-learn. Emphasis is put on ease of use, productivity, flexibility, performance, documentation, and an API consistent with scikit-learn. It depends on scikit-learn and pymc3 and is distributed under the new BSD-3 license, encouraging its use in both academia and industry. Source code, binaries, and documentation are available on http://github.com/pymc-learn/pymc-learn.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Daniel Emaasit

Daniel Emaasit

Data Scientist, Haystax
I am a Data Scientist at Haystax in Washington, D.C. My interests involve developing principled probabilistic models for problems where training data are scarce by leveraging knowledge from subject-matter experts and context information. In particular, I am interested in flexible... Read More →

Sponsors

Thursday April 11, 2019 11:15am - 11:45am EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

11:45am EDT

Applied Machine Learning Conference: Networking Lunch
Networking Lunch for the Applied Machine Learning Conference Guests, Speakers, and Exhibitors.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.


Thursday April 11, 2019 11:45am - 12:45pm EDT
Violet Crown 200 W Main St, Charlottesville, VA 22902, USA

12:45pm EDT

Deep Learning for Visual Recognition of Enteropathy and Addressing Tissue Staining Color Bias in Biopsy Slides
Pathology has played an essential role in diagnosis of gastrointestinal disorders. However, errors can occur due to complex systems, time constraints and variable inputs. This can be further complicated when the biopsy images share histological features. In light of this, developing assistive computational methods can help. The goal of applying computational methods in identifying diseases is to achieve a fast, reproducible and reasonably accurate methods that can be standardized. 
Deep learning in detecting diseases in histopathology images has been an active area of research. Convolutional Neural Networks (CNN), a form of deep learning, is particularly suited for distinguishing features in biopsy images. Past work in this area involves using CNN to detect cancer metastases in high resolution biopsy images. 
Applying CNN to high resolution biopsy images from patients of gastro-intestinal diseases, specifically, Celiac Disease and Environmental Enteropathy helps detect distinguishing features in tissues effected by them. These diseases have significantly overlapping features which makes them difficult to be diagnosed. CNNs learn from different areas of an image and look for similar patterns in new images and classify them based on which features look the same. Our hypothesis is this deep learning technique will find differences in histologically similar looking tissues that are sometimes indistinguishable under a microscopic lens. 
We demonstrate in our work a viable deep learning architecture to classify duodenal biopsy images into if each of them is either has Celiac Disease, Environmental Enteropathy or Normal tissues. We build a model using a Resnet50 CNN model, pre-trained on the ImageNet dataset. We use transfer learning and differential learning rates to further train the model. We run color normalization on our dataset to remove color differences that occur in images caused due to using different reagents while staining or different scanning machines. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Aman Shrivastava

Aman Shrivastava

Student, University of Virginia
I am a Data Science masters student at the Data Science Institute, University of Virginia. With an eclectic background through my education and engagements with organizations in different domains, I am passionate about finding interdisciplinary applications of data science, particularly... Read More →

Sponsors

Thursday April 11, 2019 12:45pm - 1:00pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

12:45pm EDT

Intelligent Virtual Assistants - The Good, Bad, and Ugly
Intelligent Virtual Assistants (IVAs) have opened up a new world of convenience in home and work ecosystems. Waking up in the morning and finding out, with a simple question, how the weather is or what is your schedule, completing your shopping list with a simple verbal request. IVA are also integrated and connected with other IoT smart home devices, we can ask to increase the temperature in the apartment, to prepare a coffee, show the baby camera, or open the garage door. This rapid expansion of IVA is a game changer with good and bad outcomes. Gartner predicts that the IVA market will increase to over 2.1BN by 2020. However, it appears that as we surround ourselves with more and more IVA devices, more and more news reports are delivering stories that are raising concerns regarding the reliability and trustworthiness of such IVAs. Such as our parrot is adding items in our shopping list, kindergartener accidentally ordering pricey toy, IVA is calling police without user interaction.

In this presentation we will discuss the IVA core architectures and the security and privacy concerns raised by their integration into home and work environments. We would employ statistical methods to ‘fingerprint’ IoT devices including IVA and would identify device state such as active, muted, and idle. We would discuss network traffic similarity analysis between IoT devices in smart home, and their link and communication patterns. The questions that are addressed in this presentation are:
  1. Can we identify the IoT devices in our home network by looking at the traffic?
  2. Is the network traffic similar among the IoT devices from the same manufacturer?
  3. Can we discover the communication pattern between devices by looking at the traffic?

This presentation will conclude with a brief discussion of our future research focused on leveraging the IoT device fingerprinting approach to identify malicious behavior or deviations from normal behavior that may raise security concerns.

The presentation session is organized in five parts each consist of lecture and interactive sections:
  • Introduction to IVA and Smart Home IoT networks
  • Architecture of IVAs (Alexa, Google assistant, Siri, Cortana)
  • Security and privacy vulnerabilities scenarios
  • Demonstrating of practical example – ML code and real-world data
  • Conclusion

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Olivera Kotevska

Olivera Kotevska

Postdoctoral researcher, Oak Ridge National Laboratory
Olivera Kotevska is a postdoctoral researcher in Computer Science and Mathematics at Oak Ridge National Laboratory (ORNL), Tennessee, USA. Olivera received her Ph.D. degree in Computer Science from the University of Grenoble Alpes, Grenoble, France in 2018. Before joining ORNL, she... Read More →

Sponsors

Thursday April 11, 2019 12:45pm - 1:00pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

12:45pm EDT

Intro to ConvNets: The Backbone of Modern Computer Vision
In recent years, advancements in deep learning have revolutionized the field of computer vision. Tasks like image classification have surpassed human performance on several complex datasets, and great strides are being made on several other areas such as object detection, face recognition and image segmentation. Behind this revolution lies a simple yet effective algorithm, the Convolutional Neural Network (CNN). In this talk, Tryolabs Research Engineer Joaquin Alori gives a brief history behind the progress of CNNs, explains how they work, and shows how they are being used in state of the art models.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Joaquín Alori

Joaquín Alori

Research Engineer, Tryolabs
Joaquin Alori is a Research Engineer at Tryolabs, where he works on object tracking, pose estimation, and person re-id problems. Prior to joining Tryolabs he worked at ABB Uruguay as a Control Systems Engineer. He holds a BS in Manufacturing Engineering from Universidad de Montev... Read More →

Sponsors

Thursday April 11, 2019 12:45pm - 1:00pm EDT
Violet Crown: Theater 2

12:45pm EDT

TensorFlow in R Programming, A Beginner's Primer
Developed by Google researchers and engineers for  deep neural networks research, Tensorflow provides developers a capacity for developing deep learning models. It and the Keras framework became available for R programming in 2018, along with an availability for machine learning in the browser through the Tensorflow.js framework. But how should developers approach using the basic capabilities in Tensorflow? This session is a straightforward overview of how the machine learning framework is used within R. Examples with data will be presented with coverage of how to best start with the framework.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Pierre DeBois

Pierre DeBois

Founder / CEO, Zimana
Pierre DeBois is the founder and CEO of Zimana, an analytics services that help organizations achieve profitability improvements in marketing, Web development, and within their business operations. Zimana has provided services for businesses from many industries.Pierre has provided... Read More →

Sponsors

Thursday April 11, 2019 12:45pm - 1:00pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

1:05pm EDT

Collaboration between Data Scientist and Librarian/Project Manager
This is a solo presentation designed to illustrate the way data science techniques can be used to make practical decisions in managing a project. The genesis of the collaboration occurred when the librarian/project manager and data scientist began working together in the library setting and explored possibilities of integrating data science into library data gathering and analysis, to foster informed decision-making.

The collaboration became a reality when the librarian/project manager was faced with moving the 1.675 million book collection out of the main library for a major renovation project. She formed a Data Working Group comprised of the data scientist, two library employees skilled at gathering relevant data, and herself. The Group analyzed the large library collection to aid the Alderman Renovation Collections Group in determining which books should remain on-campus during the renovation and which could be located at and retrieved from the Library’s off-site facility.

The end result was the creation of a picklist for the books remaining on-campus and it has been given to the vendor who will actually do the move. This was completed at the end of December 2018 and was the key element to the successful resolution of managing the collection during the expected three-year renovation when the large, main library will be closed.


You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Esther Onega

Esther Onega

Senior Project Manager for Alderman Renovation, University of Virginia Library
Ms. Onega has worked at the UVA Library since 1997, in a variety of librarian and project management positions. She received her MLS from University of Maryland and her Project Management certificate from the University of Virginia. Her strengths include a thorough knowledge of the... Read More →

Sponsors

Thursday April 11, 2019 1:05pm - 1:20pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

1:05pm EDT

Design of Semiconducting Materials for Photovoltaic Applications Using Python Machine Learning with Tensor Flow
This presentation will detail the steps used to build a TensorFlow machine learning model to predict the band gap of semiconducting materials. The band gap is a fundamental property determining photovoltaic-device efficiency for applications such as solar panels. The optimal band gap range for these applications is 0.5eV - 2.5eV. Our dataset was generated from the open source Materials Project and the Python Materials Genomics (pymatgen) code and database. After generation of the dataset and elemental physical descriptors (features), we proceeded to create a “pipeline” of models to facilitate feature engineering and feature selection. First, we developed a support vector machine regression model with a radial-basis (gaussian) kernel and employed a grid search to get a RMSE of 0.45eV.   Although this model gave good results, each dataset instance consisted of 128 features, and we sought to reduce this initial feature space to avoid model complexity and overfitting. 
As part of feature engineering through our “model pipeline”, we employed Random Forest and its feature importance measures to reduce the feature space dimensionality. Finally, with the reduced feature space, we build a machine learning model in TensorFlow with L2 regularization (ridge regression). Through judicious hyperparameter tuning of our TensorFlow model and using element-specific atomic descriptors, we predict the band gaps of more than 75 AB binary compounds suitable for photovoltaic applications. A root mean squared error (RMSE) of 0.2 eV is achieved using the TensorFlow model with only a 10-dimensional set of descriptors, reduced from the 128-dimensional feature space we started with!
The resulting TensorFlow model can be deployed to discover new materials that can be used in applications with the goal of reducing the world’s carbon footprint such as solar panels for generating electricity and water splitting devices for hydrogen fuel cells.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Anthony Teate

Anthony Teate

Professor, James Madison University
Dr. Anthony A. Teate is a tenured Professor in the School of Integrated Sciences located in the College of Integrated Science and Engineering at James Madison University, where he is also the Director of the Data Science and Applied Machine Learning Laboratory. His current areas of... Read More →

Sponsors

Thursday April 11, 2019 1:05pm - 1:35pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

1:05pm EDT

Detecting The Unknown: Using Unsupervised Behavior Models To Expose Malicious Network Activity
We'll describe our work to achieve anomaly detection at network speed by combining probabilistic modeling, graph-based models, and more traditional machine learning techniques with the open source RAPIDS suite of software libraries. Traditional approaches to cybersecurity take a reactive approach, studying previous attacks to flag similar attacks in the future. This leaves systems vulnerable to day zero attacks in which adversaries use entirely new tactics to infiltrate a network. We'll explain how we address this issue by using multiple unsupervised models to alert cyber analysts about anomalous behavior, and then incorporate analysts' feedback to continuously update our models. The nature of anomaly detection in this low signal-to-noise space results in a high-false positive rate for most machine learning approaches. To mitigate this, we incorporate cyber analysts' feedback on alerts to continuously update our models. By combining the power of machine learning with experts' cyber knowledge in one integrated learning platform powered by GPUs, we improve the accuracy of future alerts, overall model performance, and reduce the time to detection for novel attacks. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Will Badart

Will Badart

Machine Learning Engineer, Booz Allen Hamilton
Will is a web developer turned software engineer turned data scientist at Booz Allen Hamilton. At Booz Allen, Will designs and builds novel, AI-driven cyber defenses and systems to deliver them. Will has a passion for design, vim, martial arts, and open source software.
avatar for Sarah Olson

Sarah Olson

Data Scientist, Booz Allen Hamilton
Sarah Olson is a Data Scientist at Booz Allen Hamilton, with current focus areas in cyber security, machine learning models, and natural language processing. Her projects at the company have supported a variety of her interests, ranging from developing models to detect credential... Read More →

Sponsors

Thursday April 11, 2019 1:05pm - 1:35pm EDT
Violet Crown: Theater 2

1:05pm EDT

Devops in Data Science Panel
You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Miriam Friedel

Miriam Friedel

Director of Data Science, Skafos.ai
Dr. Miriam Friedel has spent over fifteen years in scientific and technical fields spanning theoretical physics, software engineering, transportation, neuroscience, and machine learning. She currently leads the data science team at Skafos.ai (formerly Metis Machine) in Charlottesville... Read More →
avatar for Steven Lott

Steven Lott

Master Software Engineer, Capital One
Steve has been developing software since computers were large, expensive, and rare. He's written several books on Python, published by Packt.
avatar for Ken Zamkow

Ken Zamkow

General Manager for United States, run:ai
Ken leads the US activity for run:ai, a startup that helps deep learning engineers and data scientists to significantly speed up the training of their neural network models, while reducing compute costs and workflow complexities.Previously, Ken was the Founder and CEO of SportsGuru... Read More →

Sponsors

Thursday April 11, 2019 1:05pm - 1:40pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

1:25pm EDT

Getting Started with Robust Data Analysis - Setting Up a Data Warehouse without a Data Engineer
It’s commonly stated that 50-80% of data analysis is actually data preparation. In this talk we’ll walk through a  fast and easy way to centralize your data, model it effectively and run analyses and visuals for your stakeholders - with minimal engineering resources. Data analysts, scientists and ml engineers can’t do their work without well-formed data structures. By building out a well structured data warehouse you can increase analysis speed, repeatability and confidence.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Stephen Levin

Stephen Levin

Special Projects, Zapier
Stephen does Special Projects for the CEO at Zapier, a workflow automation tool used by over 3 million people to connect the work apps they use every day. He uses data to help inform decisions in product, strategy, marketing, and operations. He also founded Think Analytically, where... Read More →

Sponsors

Thursday April 11, 2019 1:25pm - 1:40pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

2:00pm EDT

How Can “Data for Good” Be Better?
The potential value of data science to governments, nonprofits, advocacy groups, and political campaigns is enormous, but so are the challenges. Andrew Therriault has spent most of his career working on these problems, and he’ll share the lessons he’s learned from both successes and failures. Using examples from his own work and others’, Therriault will show how to find the best opportunities to apply data science to civic problems, and offer guidance for avoiding common mistakes along the way. He’ll also take a look at the “Data for Good” ecosystem as a whole and present a new model for collaboration between the public and private sectors, one that could help civic data science finally realize its full potential.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Andrew Therriault

Andrew Therriault

Manager, Infrastructure Data Science, Facebook
Andrew Therriault has spent the past decade building and leading data science programs for organizations across the political, nonprofit, government, and technology sectors. He founded the Democratic National Committee’s data science team in 2014 and was appointed the City of Boston’s... Read More →

Sponsors

Thursday April 11, 2019 2:00pm - 2:30pm EDT
The Jefferson Theater 110 E. Main Street, Charlottesville VA 22902, USA

2:50pm EDT

Applying Machine Learning to Dynamic Operations
There is significant rhetoric about Machine Learning, but less clarity on how it’s being applied to solve operational problems.  The majority of reinforcement-based machine learning systems continues to face limitations.  Those limitations include: Variance due to multivariate nature of the operations it’s learning, Latency due to the nature of the reinforcement learning model, Bias due to the manual feature engineering and tuning that happens.
We will first explore the challenges facing ML as it attempts to predict operational systems.  Most operational systems are non-deterministic so we will assume it is that type of system that we are trying to develop an advance predictive model of.  
Assume first that system is static, single variate, and we can use a learning representation to generate a probabilistic set of outcomes.  After repeated runs we would develop a model of the outcomes.  
Accurately representing that model so that it could be used to predict future outcomes would involve some type of tuning.  Current machine learning involves complex feature analysis and manual tuning over repeated runs to achieve a model that does not over fit or underfit, so that it can accurately predict future outcomes.
But most systems are multi-variate (have multiple variable inputs) that drive their various outcomes.  This multi-dimensionality factorially increases the complexity of the model we are trying to construct; as there are many combinations of values, across many combinations of inputs, that create the varying outcomes.  
Finally, most systems are dynamic rather than static.  So not only do the multivariate input values change dynamically, their correlation to the outcomes also changes dynamically.  This dynamic adds the requirement of continuous learning, in addition to that of continuous forecasting.
Is it possible to construct a system that can effectively learn and predict this kind of model?
This discussion will explore this problem of modeling dynamic Business Operations and the challenge it presents to Reinforcement Learning.  Then we will share practical examples of applying such types of machine learning to dynamic business operations, to improve operational outcomes.  In all cases, the goal of the system is to predict future events, such that people, equipment and processes can be optimized, and disruption minimized.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Tom Brock

Tom Brock

CEO, ConvergentAI
Tom brings over 30 years experience in software and analytics.  He has had roles ranging from COO, CIO, GM and Strategy, spanning from industrial automation to healthcare analytics.  He has BS degree in Electrical Engineering from Georgia Tech, is a graduate of GE’s management... Read More →

Sponsors

Thursday April 11, 2019 2:50pm - 3:20pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

2:50pm EDT

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
In this work we analyze visual recognition tasks such as object and action recognition, and demonstrate the extent to which these tasks are correlated with features corresponding to a protected variable such as gender. We introduce the concept of “natural leakage” to measure the intrinsic reliance of a task on a protected variable. We further show that machine learning models of visual recognition trained for these tasks tend to exacerbate the reliance on gender features. To address this, we use adversarial training to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in the extent to which models rely on gender features while maintaining most of the accuracy of the original models. These results even surpass a strong baseline that blurs or removes people from images using ground-truth annotations. Moreover, we provide convincing interpretable visual evidence through an autoencoder-augmented model showing that this approach is performing semantically meaningful removal of gender features, and thus can also be used to remove gender attributes directly from images.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Tianlu Wang

Tianlu Wang

Graduate Student, University of Virginia, Department of Computer Science
Tianlu Wang is a Ph.D. student at the Department of Computer Science at the University of Virginia. She has been working with Prof. Vicente Ordóñez Román since Fall 2016. Her research focus lies at the intersection of computer vision and natural language processing. More recently... Read More →

Sponsors

Thursday April 11, 2019 2:50pm - 3:20pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

2:50pm EDT

Using Triangulation to Evaluate Machine Learning Models
As machine learning grows in prominence, adoption in high-impact use cases such as anti-fraud and network security are growing. Having a high performing statistical model in these areas are critical: a false positive error leads to unnecessary work, while a false negative error increases exposure to potential threats. Since there are no perfect machine learning models, as data scientists our task is to first convince ourselves and then convince others that we have a statistical model worthy for production. Persuasion, though, can be difficult because many of the steps and assumptions that go into training a statistical model from data are difficult, if not impossible, to accurately share with the ultimate consumers of the model. 
Drawing on ideas from the philosophy of science such as falsifiability and counterfactuals, we present a framework for triangulating the performance of machine learning models using a series of questions to help establish the validity of performance claims. In navigation tasks, triangulation can be used to determine one’s current location based on the angle and distance from other landmarks with known position. We believe triangulation of a different sort is necessary to determine the performance of machine learning models. Each of the steps that go into making a machine learning model including input data selection, sampling, outcome variable selection, feature creation, model selection and evaluation criteria shape the final model and provide necessary context for interpreting the performance results. Our framework highlights ways to uncover assumptions hidden in those choices and identify higher performing models. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Andrew Fast

Andrew Fast

Chief Data Scientist, CounterFlow AI, Inc
Andrew Fast is the Chief Data Scientist and co-founder of CounterFlow AI, where he leads the implementation of streaming machine learning algorithms on CounterFlow AI's ThreatEye cloud-native analytics platform for Encrypted Traffic Analysis. Previously, Dr. Fast served as the Chief... Read More →

Sponsors

Thursday April 11, 2019 2:50pm - 3:20pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

2:55pm EDT

MRI Image Synthesis for the Diagnosis of Parkinson's Disease
Parkinsons disease (PD) is a neurodegenerative disease that affects an estimated 1% of adults over 65. While the disease itself is not fatal, complications related to PD are rated as the 14th largest cause of death in the United States by the Center of Disease Control and Prevention. In spite of technological advances, Parkinson’s diagnosis methods have not changed, and the accuracy of diagnosis has remained at approximately 81% for the past 25 years. These methods include analyzing years of neurological data to determine if the patient has developed the symptoms of Parkinson’s, including limb rigidity and tremors, both of which are common side effects of a number of other diseases. With the rise of automated prediction algorithms paired with the generation of massive amounts of data, the automatic diagnosis of Parkinson’s Disease has not caught up to traditional means. This is commonly attributed to the lack of useful data, as most computational systems require a tremendous amount of medical data that isn’t readily available as gathering the data can be expensive. This study presents PDGAN, a tool to aid pathologists and neurologists in the diagnosis of Parkinson’s Disease. PDGAN uses a series of neural networks to classify Magnetic Resonance Images (MRI Images). PDGAN employs Generative Adversarial Networks (GANs) to synthetically generate medical images which is used to augment the classification efforts. The pair of Convolutional Neural Networks exhibited an testing accuracy of 91.4% without the augment of new data, and combined the total accuracy was 96.6%, a 16% increase com- pared to traditional methods at a fraction of the cost and time. PDGAN demonstrates the feasibility of utilizing GANs to generate unseen data for the improvement of classification accuracy in the medical setting. The biggest challenge in leveraging the power of AI/ML in the healthcare space today is a lack of data access. What if we could artificially generate more data to fill in the gaps where traditional patient-driven sampling techniques don’t meet the data demand? This session presents one use-case for Generative Adversarial Networks and Auto-encoders to augment a data-set, as well as other optimization techniques for classifiers working with small amounts of data. This session will demonstrate these concepts in the scope of an important problem in the field of healthcare: accurately assessing Parkinson’s onset for a quick diagnosis. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Neeyanth Kopparapu

Neeyanth Kopparapu

Student, Thomas Jefferson High School for Science and Technology
Neeyanth Kopparapu is a High School Junior at Thomas Jefferson High School in Alexandria, VA. As a student, he is interested in mathematics, computer science, and physics. He is especially interested in developing computer science (specifically artificial intelligence) models to help... Read More →

Sponsors

Thursday April 11, 2019 2:55pm - 3:25pm EDT
Violet Crown, Theater 1 200 W Main St, Charlottesville, VA 22902, USA

3:20pm EDT

Exploring Music Signature Embeddings with Machine Learning using Google AI's Magenta
Embeddings, representational vectors of features within a high dimensional space, are increasingly growing in popularity in domains spanning natural language processing, biomedical engineering, and geospatial decision making. Applications of embeddings are especially demonstrated in audio processing, where popular semantic models such as Word2Vec and GloVe aid in the feature identification, classification, and diagnosis of converted sound to text data. Conversely, when phonemes and semantics are of less importance, audio waveforms themselves are embedded using features such as amplitude, frequency, and phase shift.
Unfortunately, little research exists surrounding visual embedding representations of the audio waveforms. CCRi’s prior research conducted on track image chips suggest that image signatures of geospatial events embed to provide just as meaningful observations as the geocoordinates themselves. Following this example through an ensemble of Magenta--an opensource Python library for music and image manipulation--and CCRi’s image processing software, we will demonstrate to what degree music signatures successfully cluster together in embedding space and whether classifications can be made from these findings.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Malcolm MacLachlan

Malcolm MacLachlan

Software Engineer, CCRi
Malcolm is a software engineer at CCRi. He has experience building web and mobile applications for data analytics. He is interested in the intersection of music and technology and co-owns a record label based out of Detroit, MI.

Sponsors

Thursday April 11, 2019 3:20pm - 3:35pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

3:20pm EDT

Get Your Results Seen & Understood More Quickly with Visual Metaphors
How many eyes have you seen glaze over once you say the word “algorithm”? So many projects don’t see the light of day because people can’t champion what they don’t understand. How can you effectively communicate your analysis and results to an audience? Enter the humble visual metaphor. Humble because we use them so often that we don’t even notice! (e.g. the three metaphors crammed into the preceding sentences - eyes are doughnuts that can be glazed, projects are people that can see the sun and be championed, and visual metaphor is a person that can be humble). 
No one understands your work like you do, because you’re neck-deep in it all day. So when your audience is thrown in, they can drown in the details. But you can use visual metaphors as a life vest. They’re so effective because they use your audience’s existing knowledge to help explain the unfamiliar. 
When you learn how to incorporate visual metaphor into your presentations or charts, you are building a bridge from your analysis to a concept that your audience already understands. This technique not only has the benefit of communicating more effectively, but also making your work more memorable.
So how can you incorporate visual metaphor in your work? There are so many ways! You can simply use color and text like this famous example. Or use something that everyone understands (like dominos falling) as a structural metaphor for a complex concept like this example of backpropogation. In this session, you’ll learn some tactics to make your work get seen and understood by more people with the power of visual metaphors.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Alli Torban

Alli Torban

Data Visualization Designer, American Enterprise Institute
Alli Torban is a Data Visualization Designer for the American Enterprise Institute in Washington, D.C. where she transforms public policy research into meaningful graphics for decision-makers and the general public. She’s passionate about revealing the patterns and insights hidden... Read More →

Sponsors


Thursday April 11, 2019 3:20pm - 3:35pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

3:25pm EDT

Modeling and Forecasting Hospital Workforce Supply to Improve Outcomes
I will present initial findings from a project involving a large academic medical center looking to develop a predictive system that optimizes nurse staffing. The hospital is looking to reduce costs and improve patient care by staffing the right number of nurses, with the right skills and experience, on every shift, across every unit. I will discuss how we are integrating nurse workforce data to understand labor supply variations and compare this to patient demand — including volume predictions as well as patient condition metrics. Using forecasting models, optimization, and machine learning we are building a system that will recommend optimal staffing levels for each unit so that nurse managers can staff more accurately, reducing over- or under-staffing for a given period. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for John Harris

John Harris

Data Scientist, Cogit Analytics
John is the chief data scientist for Cogit Analytics. He has extensive experience designing and building advanced analytics, machine learning, and other quantitative solutions in supply chain, finance, and healthcare.

Sponsors

Thursday April 11, 2019 3:25pm - 3:40pm EDT
Violet Crown, Theater 1 200 W Main St, Charlottesville, VA 22902, USA

3:45pm EDT

Glass Boxes: Building Trust in Machine Learning for IIoT
To reach its full potential in industrial IoT, machine learning models must be applied automatically to drive efficiency, optimize performance, and prevent catastrophic events. But before that can happen, organizations must learn to trust these models. Industrial operators are understandably hesitant to turn over control of mission-critical systems to the machines, in part because machine learning algorithms are often opaque, complex, and difficult to explain. This talk will define the nature of the trust problem for machine learning in industrial IoT and discuss the often-overlooked importance of model explainability, presentation, and trust-building. We will demonstrate tools and techniques for presenting and explaining models, as well as using models more in creative ways that go beyond mere prediction. These tools will allow us to understand models more fully, use intuition and domain expertise to identify issues more easily, and ultimately establish the trust necessary to apply models automatically and at scale.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Brad Johnson

Brad Johnson

Data Scientist, TwinThread
With a background in startup tech and consulting, Brad’s career in machine learning and industrial IoT kicked into high gear with a project helping Hershey produce Twizzlers more efficiently. As lead Data Scientist at TwinThread, Brad enjoys working on applying (and explaining... Read More →

Sponsors

Thursday April 11, 2019 3:45pm - 4:00pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

3:45pm EDT

Ethics in AI Panel
Speakers
avatar for Mo Johnson

Mo Johnson

Community Lead, Data for Democracy
Maureen (Mo) Johnson has a background in public health, anthropology and social science research. She has worked and studied in Europe, North and South America, and Asia. Because of these diverse cultural and linguistic experiences, she became interested in digital cooperation, data... Read More →
avatar for Anton Korinek

Anton Korinek

Associate Professor, UVA Economics and Darden
Anton Korinek is an Associate Professor at the Department of Economics and the Darden School of Business at the University of Virginia. His current research focuses on the implications of rapid progress in Artificial Intelligence for inequality, work, and for the future of humanity... Read More →
avatar for Tianlu Wang

Tianlu Wang

Graduate Student, University of Virginia, Department of Computer Science
Tianlu Wang is a Ph.D. student at the Department of Computer Science at the University of Virginia. She has been working with Prof. Vicente Ordóñez Román since Fall 2016. Her research focus lies at the intersection of computer vision and natural language processing. More recently... Read More →

Sponsors

Thursday April 11, 2019 3:45pm - 4:20pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

3:50pm EDT

Points to Videos: Extracting Behavioral Information from Maritime Tracks Using Convolutional Neural Networks
Extracting semantic information from point-wise observations at scale is a complex problem usually solved by using traditional brute force spatial analysis techniques. These techniques employ rigid rule-based approaches that, though somewhat accurate, fail to understand cases outside the given rule set and are computationally expensive. 
To address these shortcomings, CCRi has explores new ways to efficiently analyze tracks by encoding spatiotemporal components in a joint representation in the video domain. In this presentation, we will show the usefulness of convolutional feature extraction compared to traditional kinematic analysis practices, and demonstrate extraction of behavioral information for maritime vessels in large regions in an effort to detect illicit activities. An example of such activities is the monitoring of fishing transhipment behaviors, where smaller fishing vessels off-load their catch to large reefer vessels to maximize fishing yield in international waters, severely depleting natural fishing grounds. The presentation will include a collection of animated visualizations to illustrate the aforementioned solutions. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Martin Chobanyan

Martin Chobanyan

Data Scientist, Commonwealth Computer Research, Inc. (CCRi)
Martin is a data scientist at Commonwealth Computer Research. His most recent work involves using computer vision and deep learning to localize targeted behaviors from maritime vessel trajectory data. He recently graduated from the University of Virginia with a bachelors in mathematical... Read More →

Sponsors

Thursday April 11, 2019 3:50pm - 4:05pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

3:50pm EDT

Machine Learning as a Tool to Address HIV Health Disparities
HIV infection is a world-wide epidemic with almost 20 million people infected and tens of millions of deaths since the early 1980’s.  Due to better healthcare access and treatment, HIV morbidity and mortality in the US isn’t as dire for some subpopulations and has declined ~ 19% between 2005-2016. Unfortunately, there are specific demographic groups in the US which carry the burden of the disease far more than others. African Americans, especially those living in the South, lag behind other regions of the US in key HIV prevention and care indicators resulting in disparities in HIV incidence and prevalence. With the knowledge these disparities are not adequately accounted for through high-risk sexual behavior like the frequency of unprotected intercourse or the number of sexual partners, new tools are desperately needed to assist in addressing the disparities in HIV incidence /prevalence in minority communities.
This talk proposes to cover the following: 1) Highlight recent applications of machine learning in studies on HIV, 2) Discuss the downsides of ML healthcare, and 3) Present the results of a novel HIV health disparities study, applying machine learning/logistic regression techniques.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Kimberly Deas

Kimberly Deas

Health Data Scientist, Rutgers University
Kimberly is a Health Data Scientist Consultant who works with for and non-profit organizations, academic institutions, and government agencies, providing statistical and data analytical support to their programs. Formerly educated in Chemistry and Pharmacology at the University of... Read More →

Sponsors

Thursday April 11, 2019 3:50pm - 4:20pm EDT
Violet Crown, Theater 1 200 W Main St, Charlottesville, VA 22902, USA

4:05pm EDT

Machine Learning on Mobile
This talk will cover the ways to approach machine learning on mobile devices. I am going to compare cloud-based and on-device inference, focusing more on the latter. Local (on-device) machine learning means that inference is happening directly on a mobile device, giving us the benefit of keeping the user's data private and not depending on the network connection. However the ML models should be prepared and optimized for efficiency and performance. I will do an overview of different ML frameworks that work on iOS and Android, namely: CoreML, MLKit, and TensorFlow Lite. The attendees will understand the capabilities and limitations of each of these frameworks, and will have a general idea of how ML models should be prepared for deployment on mobile.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
TC

Tatyana Casino

Platform Software Engineer, WillowTree
Tatyana Casino is a software engineer at WillowTree, a mobile innovation agency. Tatyana has been building mobile apps for a variety of leading brands and clients. She has been developing for Android for 5 years, has done cross-platform development with Xamarin and worked on native... Read More →

Sponsors

Thursday April 11, 2019 4:05pm - 4:20pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

4:05pm EDT

Mapping High-Voltage Infrastructure with Machine Learning + Humans
Over 1.2 billion people around the world lack access to electricity. In developing nations, this problem is especially acute as it limits participation in modern economy and culture. Improving the electric grid, however, is often logistically challenging in these regions because there is rarely a complete and accurate map of the existing electric infrastructure. This map is crucial as there is no way to make informed decisions on how to spend resources to improve the electric grid without it.
Toward solving this problem, we built a pipeline to efficiently map the high-voltage (HV) grid at a country-wide scale. This pipeline relied on both machine learning (ML) and our Data Team -- a group of eight professional mappers. The ML component processed satellite imagery across an entire target country and returned geospatial locations likely to contain HV towers -- the tall metal structures that support HV lines running for hundreds or thousands of kilometers. Our Data Team then overlaid this information on top of satellite imagery and used it as a guide to help quicken their mapping of HV towers, lines, and substations. With this overlay, they could focus their attention on high priority areas and avoid the tedious task of reviewing entire countries worth of imagery by hand.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Drew Bollinger

Drew Bollinger

Developer, Development Seed
Drew is a developer and data analyst at Development Seed. He has rich experience running advanced analysis and machine learning algorithms on large geospatial data sets. He is passionate about using powerful analysis and visualization techniques to promote social change. He is a firm... Read More →

Sponsors

Thursday April 11, 2019 4:05pm - 4:20pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Challenges in Clinical Big Data Research: A Case Discussion
A discussion of the UVA Engineering in Medicine Partnership on Sleep and Cardiovascular Research group’s experience with conducting research on a clinically- derived big data set, specifically focusing on the challenges this group has faced, and how those challenges are generalizable to all clinical big data research.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Elizabeth Harrison

Elizabeth Harrison

Dual Degree Candidate, University of Virginia School of Medicine & School of Data Science
Elizabeth Harrison is a fourth year medical student at the University of Virginia School of Medicine and a recent graduate of UVA's Master of Science in Data Science degree program. She is currently working on a number of clinical research projects involving the application of data... Read More →

Sponsors

Thursday April 11, 2019 4:25pm - 4:40pm EDT
Violet Crown, Theater 1 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Leveraging Transit Data to Identify Quality Locations for High Density Urban Development
Utilizing R to analyze a large open dataset of historical public transit ridership data via a modern suite of tools. To improve the affordable housing situation in Charlottesville, new high density urban developments are needed. Where to build these new housing units isn’t always clear, but analyzing public transit data helps inform that decisions by showing how the community gets around. Forecasting future ridership growth by bus-route gives community planners additional data to inform their selection of optimal locations for future developments in the city.
By communicating results via mapping visualizations and focusing on relevant community issues, this talk is aimed at anyone interested in urban development in Charlottesville. This talk will show off packages for time-series analysis (fable, tsibble), simple features mapping (sf) and data wrangling (tidyverse), but since the talk is results focused no coding knowledge or experience is required. Technical details of preparing data for time-series analysis and mapping spatial data, will be made available as part of the talk for audience that is more technically inclined and could be expanded on to another more code-centric talk if there is audience interest.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Nate Day

Nate Day

Data Scientist, HemoShear Therapeutics
Nathan builds analysis pipelines for drug discovery data. He utilizes Shiny applications and SQL databases to give researchers tools to explore their own experimental results. For fun Nathan practices yoga, plays squash, and helps on civic data projects. He's been living in Belmont... Read More →

Sponsors

Thursday April 11, 2019 4:25pm - 4:40pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Licensing: It's for All Projects, Yes Even Yours
With nearly 100 million repositories on GitHub alone, open source projects are proliferating. Yet, few users (~20%) apply a license to their projects. Of those selecting a license, MIT is the clear frontrunner. The selection of the license signals to anyone viewing your project how the base code can be utilized.
There are numerous types of licensing you can apply to your project, so how do you choose? Crosswalks showing various licenses and the differences are available. The biggest driver of license selection is how permissive you wish to be with your project. For instance, you may want others to have free reign on what they can do with your work? Perhaps you want others to make improvements to or use your work, but not create closed source versions? A wide variety of licenses are available to regulate legal usage of your project and recourse available to you if it is used improperly. A recent example of others financially benefiting from open source code to is the generation of art netting nearly $500,000 at auction. The creators of the A.I. model weren’t credited or compensated.
What happens if you don’t select a license? First, you are not required to select a license. If you elect to omit a licence, you retain all rights and default copyright laws apply. Simply put, if the intention is to share your work and allow others to utilize that work, your ability to do so is severely limited and put into question in the absence of a license.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Matthew Hendrickson

Matthew Hendrickson

Principal Data Analyst, HelioCampus
Matthew is passionate about data, analytics, and research. Since completing his Doctorate in Law and Policy, with a focus on Data Privacy, he muses over the legal implications of big data. However, he must balance those concerns against the tremendous benefit of amassing and analyzing... Read More →

Sponsors

Thursday April 11, 2019 4:25pm - 4:40pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Lightning Talks: A Comparison of Neural Network Methods for Accurate Sentiment Analysis of Stock Market Tweets
Sentiment analysis of Twitter messages is a challenging task because they contain limited contextual information. Despite the popularity and significance of this task for financial institutions, models being used still lack high accuracy. Also, most of these models are not built specifically on stock market data. Therefore, there is still a need for a highly accurate model of sentiment classification that is specifically tuned and trained for stock market data. 
Facing the lack of a publicly available Twitter dataset that is labeled with positive or negative sentiments, in this paper, we first introduce a dataset of 11,000 stock market tweets. This dataset was labeled manually using Amazon Mechanical Turk. Then, we report a thorough comparison of various neural network models against different baselines. We find that when using a balanced dataset of positive and negative tweets, and a unique pre-processing technique, a shallow CNN achieves the best error rate, while a shallow LSTM, with a higher number of cells, achieves the highest accuracy of 92.7\% compared to baseline of 79.9\% using SVM. Building on this substantial improvement in the sentiment analysis of stock market tweets, we expect to see a similar improvement in any research that investigates the relationship between social media and various aspects of finance, such as stock market prices, perceived trust in companies, and the assessment of brand value. The dataset and the software are publicly available. In our final analysis, we used the LSTM model to assign sentiment to three years of stock market tweets. Then, we applied Granger Causality in different intervals to sentiments and stock market returns to analyze the impact of social media on stock market and visa versa.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.


Thursday April 11, 2019 4:25pm - 5:00pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Lightning Talks: Building Data Science Microservices
Many data scientists work on their local machines and share models or analyses by sharing the code. This model does not scale well: it can lead to reproducibility issues as changes are made locally and not shared, there is duplication of work, and no one maintains or monitors performance centrally. This talk will describe building local microservices that can be shared by all members of a data science team. A microservice for data science accepts and input and returns an output. That input may be a feature set and the output may be a prediction, for example. This talk will walk through what a microservice is and how I approached building our first microservice.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Michael Zelenetz

Michael Zelenetz

Analytics Project Lead, NewYork-Presbyterian
Michael is a paramedic turned data scientist. He works on the analytics team at NewYork-Presbyterian and is passionate about using data to improve healthcare.

Sponsors

Thursday April 11, 2019 4:25pm - 5:00pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

4:25pm EDT

Lightning Talks: Machine Learning vs. Medical Doctor: Predicting Patient Outcome to Cardiac Resynchronization Therapy Using Machine Learning
Can a machine learning algorithm successfully select a patient who will respond to a costly, invasive surgical procedure in which outcome is extremely uncertain? Patients with ventricular dyssynchrony experience a condition in which the chambers of their hearts no longer contract at the same time. As a consequence, these patients develop heart failure (HF) which can be fatal. Fortunately, cardiac resynchronization therapy (CRT) offers life-saving benefits to these patients by using pacemakers to resynchronize ventricular contraction while reversing HF [1]. However, an alarming 30-50% of patients selected to receive the costly and invasive CRT procedure under current guidelines set by physicians at the American Heart Association (AHA) fail to respond to the treatment [2]. Outcomes after CRT are influenced by complex interactions between the physical, electrical, and mechanical properties of the heart, but machine learning may be capable of uncovering patterns between these interactions and patient response. Therefore, the objective of this study is to use machine learning to predict if a patient will respond to CRT as well as to identify clinical features important in such classification. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Derek Bivona

Derek Bivona

PhD Candidate, Department of Biomedical Engineering, University of Virginia
Derek is a third-year PhD candidate in the Department of Biomedical Engineering at the University of Virginia. As a member of the Cardiac Biomechanics Group, he develops computer models to study heart growth and remodeling in response to both disease and therapy. Derek utilizes machine... Read More →

Sponsors

Thursday April 11, 2019 4:25pm - 5:00pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

4:30pm EDT

Lightning Talks: Moving Objects in Exoplanet Mission Data: Studying the Solar System and Protecting the Earth
Understanding of the history of the solar system and answers to questions such as “How did Earth get its water?” rely heavily on the study of small bodies such as asteroids and comets as these objects are the most pristine probes of their formation regions within the solar system. In the last 30 years, studies of asteroids and comets have usually been directed towards the study of one object at a given time with a given telescope, but the advent of large area surveys for the monitoring of stars for exoplanets has offered a new data source to used by solar system astronomers. While these data are fraught with challenges including, but not limited to: limited data recording capabilities resulting in only predefined image pixels being saved, variability within images related to spacecraft motion and images with large pixels containing many objects, detection of small solar system bodies is still possible. From the measurement of brightness variations of these small rocky bodies in the solar system via time series analysis, we learn a wealth of information about shape and density of these small objects allowing us to learn about the solar system’s past, and potentially even ways to protect the Earth if one of these asteroids or comets is heading towards us. Data presented in this talk will be from projects led by the speaker using both the Kepler and TESS exoplanet missions.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Erin Ryan

Erin Ryan

Astronomer, SETI Institute
Erin Lee Ryan is an asteroid that can be found approximately 4 AU from the Sun. It's human namesake can be mostly frequently found in the Charlottesville area trying to do science on some form of imagery. She holds a bachelors in astronomy from the University of Arizona and a PhD... Read More →

Sponsors

Thursday April 11, 2019 4:30pm - 4:35pm EDT
Violet Crown: Theater 5 200 W Main St, Charlottesville, VA 22902, USA

4:45pm EDT

Applied ML for Linking Diverse Datasets at S&P
with S&P Global's Senior Data Scientist, Matthew Hawthorn. 

Thursday April 11, 2019 4:45pm - 5:00pm EDT
Violet Crown: Theater 4 200 W Main St, Charlottesville, VA 22902, USA

4:45pm EDT

Detecting Solar Farms Using Deep Learning
As environmentally-driven policy has shifted to incentivize renewable energy, large scale solar farms are being installed globally faster than can be reliably tracked by interested stakeholders. Photovoltaic solar arrays, or solar farms, can be clearly distinguished in aerial and satellite imagery, which makes solar farm detection a great candidate for deep learning. We have trained a convolutional neural network using Sentinel-2 imagery to detect the presence and extent of solar farms. As Sentinel-2 satellites have a revisit rate of 5 days on average, we are able to provide information in near real time. We have built an interactive web application that allows users to visualize and chart the growth of large scale solar farms. We will discuss how we prepared our labeled training data, how we trained a convolutional neural network, and show our model results. 

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Courtney Whalen

Courtney Whalen

Data Scientist, Astraea, Inc.
Courtney Whalen is a data scientist at Astraea, Inc., where she is using satellite imagery and machine learning techniques to answer complex global questions. She has been working as a data scientist for 5 years and has experience developing machine learning models across several... Read More →

Sponsors

Thursday April 11, 2019 4:45pm - 5:00pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA

4:45pm EDT

Ontology and Oncology: NLP for Precision Medicine
This session gives an overview of the importance of precision medicine in cancer treatment and describes an approach used by UVA in the TREC 2018 Precision Medicine workshop. The PM track aims to encourage research into precision oncology medicine to provide more relevant information to physicians and researchers.

For this task we ranked articles from a corpus of bio-medical article abstracts from PubMed and MEDLINE for relevance for the treatment, prevention, and prognosis of the disease given specific medical information about each patient.

We demonstrated using a flexible graph-based query expansion method that existing medical ontologies can be leveraged to improve precision in document relevance ranking with little to no other clinical input.


You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

Speakers
avatar for Sean Mullane

Sean Mullane

Data Scientist, UVA Health System
Sean is currently working as a data scientist in the UVA Health System while completing a Master's degree at the UVA Data Science Institute, where he is researching the applications of machine learning to protein structure prediction. He has lived in Charlottesville, VA since graduating... Read More →

Sponsors

Thursday April 11, 2019 4:45pm - 5:00pm EDT
Violet Crown, Theater 1 200 W Main St, Charlottesville, VA 22902, USA

5:00pm EDT

Applied Machine Learning Conference: Networking Happy Hour
First Drink on Us!
Netowrking Happy Hour for the Applied Machine Learning Conference Guests, Speakers, and Exhibitors.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.


Thursday April 11, 2019 5:00pm - 6:00pm EDT
Violet Crown 200 W Main St, Charlottesville, VA 22902, USA
 


Twitter Feed