Heroes of Deep Learning: Ian Goodfellow


“One way that you could get a lot of attention is to write good code and put it on Github. If you have an interesting project that solves a problem that someone working at top lab wanted to solve, once they find your github repository, they’ll find you.”

Ian Goodfellow is best known for inventing Generative Adversarial Networks (GANs), now a widely-used class of algorithms. Aside from his stints at Google Brain and OpenAI, Goodfellow recently published the textbook Deep Learning with his former advisors, Yoshua Bengio and Aaron Courville.

Andrew sits down with Goodfellow to discuss how he first discovered AI (in Andrew’s introductory class at Stanford), his current research on adversarial examples, and more.

Here’s what you’ll learn in the interview:

  • 00:14: How Goodfellow first became interested in AI
  • 2:47: The story of how Goodfellow invented Generative Adversarial Networks
  • 4:23: How a near-death experience reaffirmed Goodfellow’s commitment to AI
  • 5:25: Goodfellow’s work on GANs
  • 7:24: Details on Goodfellow’s textbook, Deep Learning, co-authored with Yoshua Bengio and Aaron Courville
  • 9:15: How Goodfellow’s thinking about deep learning has evolved
  • 11:16: Goodfellow’s advice for getting into AI
  • 13:16: Goodfellow’s current research on adversarial examples


Want to build your own career in deep learning? Get started by taking the Deep Learning Specialization.