activity
20192025
most citedWeight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape

17 citations · 29 across the 10 of their papers we have counts for

collaborators
Showing cs.NEShow all

1 paper · 1 filter

cs.NE2023

Expand-and-Cluster: Parameter Recovery of Neural Networks

Flavio Martinelli, Berfin Simsek, Wulfram Gerstner +1

Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparamete…