New In Context Podcast: Deep Learning with Graham Taylor and David Duvenaud

https://duvenaud.github.io/learn-discrete/

This episode features a conversation with machine learning researchers Graham Taylor (University of Guelph) and David Duvenaud (University of Toronto). We discuss how deep learning enables us to exploit the creative potential of framing tasks and phenomena as optimization problems.

In the podcast, you’ll learn about:

• Different types of machine creativity
• Why deep learning was a conceptual breakthrough
• What variational inference is and why it’s important
• The latest research in automating the design of deep learning architecture
• What Geoffrey Hinton and mathematician Srinivasa Ramanujan have in common

Subscribe: iTunes / SoundCloud / Google Play

Graham and David

About Graham and David

• Graham’s Webpage
• David on Linkedin
• David’s Webpage

Mentioned in the Interview

• Jürgen Schmidhuber
• Paper — A Neural Algorithm of Artistic Style
• Srinivasa Ramanujan
• Paper — Predicting Adversarial Examples with High Confidence
• Paper — Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Zoubin Ghahramani
• Variational Inference
• Learning Discrete Latent Structure