s/Cognition

=> ๐Ÿฆ‰ Moderated by: satya

=> ๐Ÿคฒ Subspaces | ๐Ÿ“– Help | โค๏ธ Code of conduct | Sign up

Posts

=> ๐Ÿฆ‰ satya [mod]

How Determinantal Point Processes supports Out-Of-Distribution Generalization โ€” Introduction Deep Neural Networks are impressively good at doing human-ish things which until recently computers just couldn't do. However, one area where humans excel but DNNs are still terrible is out of distribution generalisation (OODG) - that is, applying knowledge learned in one context to another context which has never been encountered before. Now modern AI can sort of do this in practice, since presumably...

=> ๐Ÿ’ฌ View post ยท 2024-12-16 ยท 7 weeks ago

=> ๐Ÿฆ‰ satya [mod]

Neural Nets and Non-Human Animals โ€” The question is simple: Neural networks are thought to be a roughly decent model of how the brain works, although there's a lot we don't know. Humans can do some pretty impressive things that non-human animals absolutely cannot do when it comes to analogy and representing abstract relationships. The main way neural networks get better is scaling (i.e. bigger brains). If neural nets are a good model of brains, then why is the human/animal distinction so abrupt?...

=> ๐Ÿ’ฌ 2 comments ยท 2024-10-24 ยท 3 months ago

Options

=> ๐Ÿ—ฃ๏ธ Sort by activity
=> ๐Ÿ”ฅ Sort by hotness
=> Gemini feed
=> Atom feed

Proxy Information
Original URL
gemini://osanwe.benson.earth/s/Cognition
Status Code
Success (20)
Meta
text/gemini; charset=utf-8
Capsule Response Time
429.643359 milliseconds
Gemini-to-HTML Time
1.041273 milliseconds

This content has been proxied by September (3851b).