AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
MLST #78 - Prof. NOAM CHOMSKY (Special Edition)
Machine Learning Street Talk (MLST)
Neural Networks and Compositionality
Compositionality is that the meaning of a complex expression is fully determined by its structure and the meanings of its constituents. Once we fix what the parts mean and how they are put together, we have no more lee way regarding meaning of the whole. This doesn't just apply to expressions; this also applies to planning and reasoning. It's only possible with an algebraic approach to semantics and planit achieved with symbolic manipulation. That's why neural networks cannot do basic arithmetic. They cannot represent inten al, which is to say, infinite objects. The important thing to realize is the only way to represent infinite objects in a finite way is using quantification or logic over typed symbolic structures.
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