activity
20172021
most citedDo We Really Need to Learn Representations from In-domain Data for Outlier Detection?

6 citations · 14 across the 6 of their papers we have counts for

collaborators
Showing cs.NEShow all

1 paper · 1 filter

cs.NE2018

Deep learning with asymmetric connections and Hebbian updates

Yali Amit

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic…