Recent breakthroughs in artificial intelligence are based on probabilistic programs, which go far beyond the capabilities of neural networks. MIT’s Josh Tenenbaum explains how reverse-engineering the ways in which human babies learn has enabled the development of robots that can, for example, imagine new uses for tools they have never seen before.

EVENT:

World Economic Forum 2019
Idea Labs

SPEAKER:

Josh Tenenbaum

PUBLICATION PERMISSIONS:

Original video was published with the Creative Commons Attribution license (reuse allowed).

ATTRIBUTION CREDITS:

Original video source: https://www.youtube.com/watch?v=N3hUOJ-rUzQ