Heroes of Deep Learning: Yoshua Bengio

 

“Don’t be afraid of the math. Just develop the intuitions and then the math becomes easier to understand once you get the hang of what’s going on at the intuitive level.”

Along with Geoffrey Hinton and Yann LeCun, Yoshua Bengio forms the trio of researchers who are credited with initiating the rise of deep learning in the 1990s and 2000s. Bengio is the co-founder of Element AI, a startup that provides AI business solutions. Aside from Element AI, Bengio leads the Montreal Institute for Learning Algorithms and has been a Professor of Computer Science at Montreal University since 1993. Bengio received his PhD from McGill University, then worked as a postdoctoral fellow at AT&T Bell Labs MIT under Michael I. Jordan.

Andrew sits down with Bengio to discuss his research inventions, the way he thinks about deep learning, and his advice for learners starting out in AI.

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

• 00:20: How Bengio got started in deep learning
• 3:00: Bengio reflects on his biggest successes and biggest mistakes
• 4:16 (and 8:48): Bengio’s thoughts on the relationship between deep learning and the brain
• 6:16: The research inventions that Bengio is most proud of
• 11:18: Bengio’s thoughts on unsupervised learning
• 14:30: The deep learning research areas that excite Bengio the most
• 19:09: How Bengio thinks about deep learning not just as an engineering discipline
• 21:08: Bengio’s advice for breaking into AI

 

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