Neural population geometry and optimal coding of tasks with shared latent structure

arXiv:2402.16770v2 Announce Type: replace-cross
Abstract: Humans and animals can recognize latent structures in their environment and apply this information to efficiently navigate the world. However, it remains unclear what aspects of neural activity contribute to these computational capabilities. Here, we develop an analytical theory linking the geometry of a neural population's activity to the generalization performance of a linear readout on a set of tasks that depend on a common latent structure. We show that four geometric measures of the …

abstract animals apply arxiv capabilities coding computational cond-mat.dis-nn cond-mat.stat-mech cs.lg cs.ne environment geometry however humans information population q-bio.nc tasks theory type world