all AI news
Getting aligned on representational alignment. (arXiv:2310.13018v2 [q-bio.NC] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Biological and artificial information processing systems form representations
that they can use to categorize, reason, plan, navigate, and make decisions.
How can we measure the extent to which the representations formed by these
diverse systems agree? Do similarities in representations then translate into
similar behavior? How can a system's representations be modified to better
match those of another system? These questions pertaining to the study of
representational alignment are at the heart of some of the most active research
areas …
alignment artificial arxiv behavior bio decisions diverse form information processing reason systems translate