246 citations · 552 across the 25 of their papers we have counts for
3 papers · 1 filter
Frivolous Units: Wider Networks Are Not Really That Wide
Stephen Casper, Xavier Boix, Vanessa D'Amario +4
A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests…
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
Jonas Kubilius, Martin Schrimpf, Kohitij Kar +11
Deep convolutional artificial neural networks (ANNs) are the leading class of candidate models of the mechanisms of visual processing in the primate ventral stream. While initially…
Continual Learning with Self-Organizing Maps
Pouya Bashivan, Martin Schrimpf, Robert Ajemian +3
Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they a…