Learning with "Relevance": Using a Third Factor to Stabilize Hebbian Learning

Abstract

It is a well-known fact that Hebbian learning is inherently unstable because of its self-amplifying terms: the more a synapse grows, the stronger the postsynaptic activity, and therefore the faster the synaptic growth. This unwanted weight growth is driven by the autocorrelation term of Hebbian learning where the same synapse drives its own growth. On the… (More)
DOI: 10.1162/neco.2007.19.10.2694

8 Figures and Tables

Topics

  • Presentations referencing similar topics