Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

In terms of terminology, is it accurate to interpret the latent variables as the “world model” of the neural network?


Not quite.

Embeddings are a form of latent variables.

Attention query/key/value vectors are latent variables.

More generally, a latent variable is any internal, not-directly-observed representation that compresses or restructures information from inputs into a form useful for producing outputs.

They usually capture some underlying behavior in either lower dimensional or otherwise compressed space.


How about "bias vector space"?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: