AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Melanie Mitchell: Abstraction and Analogy in AI
The Gradient: Perspectives on AI
Neural Networks and Symbolic AI
I've been looking deeply into what's called probabilistic program induction. This is an idea to, if you've given some kind of abstraction problem or new situation to represent the concept as a program. It's very compute intensive and uses a lot of expensive search. Now people are looking at using neural networks to help speed up the search sort of in the way that they were used in a deeper enforcement learning with Monte Carlo search. And yeah, I'm fascinated by that. But to me, one of the problems with neural nets and this program induction approach is it's not very dynamic.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode