AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
MLST #78 - Prof. NOAM CHOMSKY (Special Edition)
Machine Learning Street Talk (MLST)
Is There a Need for Composable, Recomposable Abstracts?
The connectionism paper says we need to have composable, recomposable, decomposable abstractions. The other important thing comes up in there is that the code that the dealgaritm and the memory are parated. This is a big difference between connectionist systems,. If you want to increase the size of the input, for example, like double the de vector space or something, it's all got to be retrained. And this is a huge difference between these these o, you know, computational paradimes.
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