We hope you can join us at one of our upcoming events — either in person or online.

Loading Events
  • This event has passed.
Sep
19

2018 Harold Pender Award Lecture: Yann LeCun: “Could Machines Be More Like Humans?”

September 19, 2018

Wednesday, September 19 | 4:00 PM - 5:30 PM EDT
Glandt Forum

ABOUT YANN LECUN 

Yann LeCun is VP and Chief AI Scientist at Facebook and Silver Professor at NYU. He is affiliated with the Courant Institute, the Center for Data Science, the Center for Neural Science, and the Electrical and Computer Engineering department. He was the founding Director of Facebook AI Research and of the NYU Center for Data Science.

ABSTRACT 

Deep learning has enabled significant progress in computer perception, natural language understanding and control. But almost all these successes largely rely on supervised learning, where the machine is required to predict human-provided annotations, or model-free reinforcement learning, where the machine learns actions to maximize rewards. Supervised learning requires a large number of labeled samples, making it practical only for certain tasks. Reinforcement learning requires a very large number of interactions with the environment (and many failures) to learn even simple tasks. In contrast, animals and humans seem to learn vast amounts of task-independent knowledge about how the world works through mere observation and occasional interactions.

Learning new tasks or skills requires very few samples or interactions with the world: we learn to drive and fly planes in less than 20 hours of practice with no fatal failures. What learning paradigms do humans and animals use to learn so efficiently? In this talk, Dr. LeCun will propose the hypothesis that learning predictive world models is the essential missing ingredient of current approaches to AI. With them, one can predict outcomes and plan courses of actions. One could argue that prediction is the essence of intelligence. Good predictive models may be the basis of intuition, reasoning and “common sense,” allowing us to fill in missing information: predicting the future from the past and present, or inferring the state of the world from noisy percepts. After a brief presentation of the state of the art in deep learning, some promising principles and methods for self-supervised learning of predictive models will be discussed.

For more information, please check here.

Location

Details

Event Organizer

  • Engineering