Ian Goodfellow: Generative Adversarial Networks (GANs) | Lex Fridman Podcast #19

The following is a conversation with Ian Goodfellow. He's the author of the popular textbook on Deep Learning, simply titled Deep Learning. He coined the term of generative adversarial networks, otherwise known as GANs, and with his 2014 paper, is responsible for launching the incredible growth of research and innovation in this subfield of Deep Learning. He got his BS and MS at Stanford, his PhD at University of Montreal with Yoshua Bengio and Aaron Courville. He held several research positions, including an OpenAI, Google Brain, and now at Apple as the director of machine learning. This recording happened while Ian was still at Google Brain. But we don't talk about anything specific to Google or any other organization. This conversation is part of the Artificial Intelligence podcast. If you enjoy it, subscribe on YouTube, iTunes, or simply connect with me on Twitter @lexfridman, spelled F-R-I-D. And now, here's my conversation with Ian Goodfellow. You open your popular Deep Learning book with a Russian doll type diagram that shows Deep Learning is a subset of representation learning, which in turn is a subset of machine learning, and finally a subset of AI. So this kind of implies that there may be limits to Deep Learning in the context of AI. So what do you think is the current limits of Deep Learning, and, uh, are those limits something that we can overcome with time?

Yeah. I think one of the biggest limitations of Deep Learning is that right now, it requires really a lot of data, especially labeled data. Um, there are some unsupervised and semi-supervised learning algorithms that can reduce the amount of labeled data you need, but they still require a lot of unlabeled data.

Mm.

Reinforcement learning algorithms, they don't need labels, but they need really a lot of experiences. Um, as human beings, we don't learn to play pong by failing at pong two million times. So just getting the generalization ability better is one of the most important bottlenecks in the capability of the technology today. And then I guess I'd also say Deep Learning is like a component of a bigger system. Um, so far, nobody is really proposing to have, uh, only what you'd call Deep Learning as the entire ingredient of intelligence. You use Deep Learning as sub-modules of other systems, like AlphaGo has a Deep Learning model that estimates the value function. Um, you know, most reinforcement learning algorithms have a Deep Learning module that estimates which action to take next, but you might have other components.

So you're basically as, uh, building a function estimator. Do you think it's, uh, possible, you said nobody's kind of been thinking about this so far, but do you think neural networks could be made to reason in the way symbolic systems did in the ’80s and '90s to do more, create more, like, programs as opposed to functions?

Yeah. I think we already see that a little bit. I already kind of think of neural nets as a kind of, of program. I think of Deep Learning as basically learning programs that have more than one step. Um, so if you draw a flowchart or, or if you draw a tensor flow graph describing your machine learning model, I think of the depth of that graph as describing the number of steps that run in sequence, and then the width of that graph is the number of steps that run in parallel. Now it's been long enough that we've had Deep Learning working that it's a little bit silly to even discuss shallow learning anymore.