Multi task representations of RNNs show a simplicity bias
Elia Turner & Omri Barak · COSYNE 2023
Recently, both experimental and theoretical work has expanded from studying neural systems with one task at a time to studying them while performing multiple tasks. An open question is understanding how a brain area, a population of inter-connected neurons, can carry on different computations depending on the context. Computations can either share the neural population code, share some activity modes, be entirely separated in activity space, or anything in between. To study this theoretically, it is possible to train RNNs on multiple tasks and study the emerging hidden representations. The cha
Sat, Mar 11, 2023