activity
20172021
most citedEmergence of grid-like representations by training recurrent neural networks to perform spatial localization

203 citations · 375 across the 4 of their papers we have counts for

collaborators
Showing 2017Show all

1 paper · 1 filter

cs.NE2017★ 141 cited

full-FORCE: A Target-Based Method for Training Recurrent Networks

Brian DePasquale, Christopher J. Cueva, Kanaka Rajan +2

Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent n…