Please log in to watch this conference skillscast.
What does deep learning and functional programming have in common? This talk dives into the basic ideas behind deep learning and deep learning frameworks like Tensorflow. You'll discover that deep learning fundamentally builds on composition, one of the central ideas in functional programming. In particular deep learning relies on composition of functions and composition of derivatives.
You will then learn how to calculate derivatives using a family of algorithms known as Automatic Differentiation and how to encapsulate these algorithms in a familiar monadic interface. From this, you will be able to build a toy deep learning system in Scala. Finally, we will look at the future of deep learning frameworks and the rise of 'differentiable programming'.
YOU MAY ALSO LIKE:
Deep Learning: Programming with a Difference
Noel is a Scala consultant at Underscore, where he helps people produce better code using Scala. He has a background in machine learning, and an abiding passion for turning his current interests into conference talks.