Deep Learning With Asymmetric Connections and Hebbian Updates

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 symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedfo...

Full description

Saved in:
Bibliographic Details
Published in:Front Comput Neurosci
Main Author: Amit, Yali
Format: Artigo
Language:Inglês
Published: Frontiers Media S.A. 2019
Subjects:
Neuroscience
Online Access:https://ncbi.nlm.nih.gov/pmc/articles/PMC6458299/
https://ncbi.nlm.nih.gov/pubmed/31019458
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3389/fncom.2019.00018
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items