Re:Space is a latent sequence: A theory of the hippocampus
by delichon on Thursday August 01, 2024 @07:11PM
(#41134609)
> I'm pretty sure the "tokenization problem" (as expressed by e.g. Karpathy) may eventually be better solved using a spatiotemporal characterization of the world
Syllables and words and phrases as gestures and movements? A paragraph as a choreography? Are we about to mash up machine learning with interpretive dance? I didn't see that one coming.
Syllables and words and phrases as gestures and movements? A paragraph as a choreography? Are we about to mash up machine learning with interpretive dance? I didn't see that one coming.