Yohan John 🤖🧠 on Nostr: npub1kq0nf…x8hsx npub1xkwas…e7jwu It also strikes me that very distributed ...
npub1kq0nfpugx8czz3u8d2wljxephk0zmn8p2y00vqhprsw8rfn7sucsvx8hsx (npub1kq0…8hsx) npub1xkwaswarxtyfywx0exf0ve9kheuzj4c6py745r6fvfm0nfz6ctlsne7jwu (npub1xkw…7jwu)
It also strikes me that very distributed representations might create problems for credit assignment: reinforcement would lead to a lot of feature-based overgeneralization.
In other words, it makes sense that conjunctive representations (logical AND like) exist and are relatively localized.
How might one design reinforcement on distributed reps that avoid/minimize such overgeneralization?
It also strikes me that very distributed representations might create problems for credit assignment: reinforcement would lead to a lot of feature-based overgeneralization.
In other words, it makes sense that conjunctive representations (logical AND like) exist and are relatively localized.
How might one design reinforcement on distributed reps that avoid/minimize such overgeneralization?