Yann LeCun on reinforcement learning, deep learning & self driving

Electrical and Computer Engineering Professor Yann LeCun shared his thoughts on a variety of technological advancements, bringing up neural nets, reinforcement and deep learning, and self driving in a Q&A feature. “The big question we need to solve is whether you observe someone like a young child, learning to manipulate objects, or a young child learning new concepts… If you were to take today’s ML systems to manipulate to recognize objects or to drive a car, it would take millions of trials, examples, and hours of practice causing many accidents. In the case of the self-driving car, this is one of the main obstacles to completely autonomous driving,” said LeCun.