Symbols and Deep Learning

4min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

Deep learning is the study of how computers learn by extrapolating data beyond their training set. It took a long time for people in the field to realize that they're actually capturing different kinds of generalization. Oogit sounds like compromise, right? I was on ex cited to set at that does sound good. So i say again, thats why we're having this podcast fornt. We're going to change it. You're doing your on. M and so you can do this on a no infinite set of things. And that's really what functions are about. Programmies about doing these things with an infinite range am identity. This is the same as that you learn the

Artificial intelligence is everywhere around us. Deep-learning algorithms are used to classify images, suggest songs to us, and even to drive cars. But the quest to build truly “human” artificial intelligence is still coming up short. Gary Marcus argues that this is not an accident: the features that make neural networks so powerful also prevent them from developing a robust common-sense view of the world. He advocates combining these techniques with a more symbolic approach to constructing AI algorithms.

Support Mindscape on Patreon.

Gary Marcus received his Ph.D. in cognitive science from MIT. He is founder and CEO of Robust.AI, and was formerly a professor of psychology at NYU as well as founder of Geometric Intelligence. Among his books are Rebooting AI: Building Machines We Can Trust (with Ernest Davis).

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.