AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min snip
Been Kim: Interpretable Machine Learning
The Gradient: Perspectives on AI
How Different Architectures Influence Different Concepts?
In theory, yes, translation in variance should happen. We don't have thato maybe governing principle across different architectures. But also, perhaps we have to go kindo beyond that and find a level of abstraction across thes different architecture. And that will be the golden goal. Our work that we published last year is to study, ok, what's in this overlap? Is there even an overlap between alfa zero and how humans play chess? Because alfa zero is self trained network. It played against itself to get that better and beat all the humans - but it has never seen how humans play Chess.
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