Using Existing Knowledge in the Algorithms

3min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

There's going to be some trad of a between letting the algaritm learn by itself, versus giving it some structure. My impression is that for chess, and the lesson was, don't spoil the algoritm by teaching it human tricks because it'll learn faster just by playing against itselfye. So another weakness in curnei as we just don't know how to leverage existing knowledge. In some cases we do, but with emphasis on the right now, it is easier just to do brute force tan,. than to have a bunch of expert go players tell you stuff.

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.