New frontiers in deep learning research with NextAI Academic Director Graham Taylor and David Duvenaud

Apr 04, 2018

This pd features a conversation with machine learning researchers Graham Taylor (NextAI Academic Director, and Associate Professor at the University of Guelph) and David Duvenaud (University of Toronto). They discuss how deep learning enables us to exploit the creative potential of framing tasks and phenomena as optimization problems. They cover a broad set of examples, like machine creativity, automating the design of neural network architecture, variational inference (that is, finding a good proxy representation of a tricky data set to make it usable for machine learning), and the mathematical structure behind making hard choices.

Read More