Tom Tom Festival 2019

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.