activity
20092023
most citedNeural population geometry: An approach for understanding biological and artificial neural networks

310 citations · 1.3k across the 14 of their papers we have counts for

collaborators
Showing 2014Show all

2 papers · 1 filter

cs.NE2014★ 69 cited

Random Walk Initialization for Training Very Deep Feedforward Networks

David Sussillo, L. F. Abbott

Training very deep networks is an important open problem in machine learning. One of many difficulties is that the norm of the back-propagated error gradient can grow or decay expo…

cond-mat.dis-nn2014★ 108 cited

Dynamics of Random Neural Networks with Bistable Units

Merav Stern, Haim Sompolinsky, L. F. Abbott

We construct and analyze a rate-based neural network model in which self-interacting units represent clusters of neurons with strong local connectivity and random inter-unit connec…