Linking task structure and neural network dynamics

Christian David Márton, Siyan Zhou, Kanaka Rajan

Abstract: The solutions found by neural networks to solve a task are often inscrutable. We have little insight into why a particular structure emerges in a network. By reverse engineering neural networks from dynamical principles, Dubreuil, Valente et al. show how neural population structure enables computational flexibility.

External IDs:doi:10.1038/s41593-022-01090-w