This is a clip from a conversation with Yann LeCun on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2NJiCov If you enjoy these, consider subscribing, sharing, and commenting below.

Full episode: http://bit.ly/2NJiCov
Full episodes playlist: http://bit.ly/2EcbaKf
Clips playlist: http://bit.ly/2JYkbfZ
Podcast website: https://lexfridman.com/ai

Yann LeCun is one of the fathers of deep learning, the recent revolution in AI that has captivated the world with the possibility of what machines can learn from data. He is a professor at New York University, a Vice President & Chief AI Scientist at Facebook, co-recipient of the Turing Award for his work on deep learning. He is probably best known as the founder of convolutional neural networks, in particular their early application to optical character recognition.

Subscribe to this YouTube channel or connect on:
- Twitter: https://twitter.com/lexfridman
- LinkedIn: https://www.linkedin.com/in/lexfridman
- Facebook: https://www.facebook.com/lexfridman
- Instagram: https://www.instagram.com/lexfridman
- Medium: https://medium.com/@lexfridman
- Support on Patreon: https://www.patreon.com/lexfridman

Elon Musk is confident that large scale data and deep learning can solve the autonomous driving problem.

What are your thoughts on the limitless possibilities of deep learning in this space?

I mean, I don't think we'll ever have a self-driving system or at least not in the foreseeable future that does not use deep learning, maybe put it this way.

So in the history of sort of engineering, particularly sort of AI-like systems.

There's generally a first phase where everything is built by hand.

Then there is a second phase, and that was the case for autonomous driving, you know, 20, 30 years ago.

There's a phase where there's A little bit of learning is used, but there's a lot of engineering that's involved in kind of taking care of corner cases and putting limits, et cetera, because the learning system is not perfect.

And then as technology progresses, we end up relying more and more on learning.

That's the history of character recognition, it's the history of speech recognition, now computer vision, natural language processing.

And I think the same is going to happen with autonomous driving, that currently The methods that are closest to providing some level of autonomy, some decent level of autonomy where you don't expect a driver to do anything is where you constrain the world.

So you only run within 100 square kilometers or square miles in Phoenix, but the weather is nice and the roads are wide, which is what Waymo is doing.

You completely over-engineer the car with tons of lidars and sophisticated sensors that are too expensive for consumer cars, but they're fine if you just run a fleet.

And you engineer the thing, the hell out of everything else.

So you have a complete 3D model of everything.

So the only thing that the perception system has to take care of is moving objects and construction and sort of, you know, things that weren't in your map.

And you can engineer a good SLAM system and all that stuff.

So that's kind of the current approach that's closest to some level of autonomy.

But I think eventually the long-term solution is going to rely more and more on learning and possibly using a combination of self-supervised learning and model-based reinforcement or something like that.


Speaker 0: Elon Musk is confident that large scale data and deep learning can solve the autonomous driving problem. What are your thoughts on the limitless possibilities of deep learning in this space?

Speaker 1: It's obviously part of the solution. I mean, I don't think we'll ever have a self-driving system or at least not in the foreseeable future that does not use deep learning, maybe put it this way. So in the history of sort of engineering, particularly sort of AI-like systems. There's generally a first phase where everything is built by hand. Then there is a second phase, and that was the case for autonomous driving, you know, 20, 30 years ago.

There's a phase where there's A little bit of learning is used, but there's a lot of engineering that's involved in kind of taking care of corner cases and putting limits, et cetera, because the learning system is not perfect. And then as technology progresses, we end up relying more and more on learning. That's the history of character recognition, it's the history of speech recognition, now computer vision, natural language processing. And I think the same is going to happen with autonomous driving, that currently The methods that are closest to providing some level of autonomy, some decent level of autonomy where you don't expect a driver to do anything is where you constrain the world. So you only run within 100 square kilometers or square miles in Phoenix, but the weather is nice and the roads are wide, which is what Waymo is doing.

You completely over-engineer the car with tons of lidars and sophisticated sensors that are too expensive for consumer cars, but they're fine if you just run a fleet. And you engineer the thing, the hell out of everything else. You map the entire world. So you have a complete 3D model of everything. So the only thing that the perception system has to take care of is moving objects and construction and sort of, you know, things that weren't in your map.

And you can engineer a good SLAM system and all that stuff. So that's kind of the current approach that's closest to some level of autonomy. But I think eventually the long-term solution is going to rely more and more on learning and possibly using a combination of self-supervised learning and model-based reinforcement or something like that.

See all Lex Fridman transcripts on Youtube

Yann LeCun on Autonomous Driving: Deep Learning is Obviously Part of the Solution | AI Podcast Clips