A Neuromorphic Normalization Algorithm for Stabilizing Synaptic Weights with Application to Dictionary Learning in LCA

Diego Chavez Arana, Alpha Renner, Andrew Sornborger

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Instabilities in neuromorphic machine learning can occur when synaptic updates meant to encode matrix transforms are not normalized. This phenomenon is encountered in Hebbian learning [5], where, as a synapse's strength grows, post-synaptic activity increases, further enhancing synaptic strength, leading to a runaway condition, where synaptic strength becomes saturated [3, 7]. A number of mechanisms have been suggested for regulating and stabilizing this phenomenon [1, 2, 4, 6]. Here, we present a new neuromorphic algorithm to directly normalize a synaptic connectivity. The algorithm is based on a synfire-gated synfire chain-based information control network in concert with Hebbian synapses [8, 10]. The algorithm is designed to directly normalize synaptic weights via the minimization of a cost function. We demonstrate its effectiveness as a component of a Locally Competitive Algorithm (LCA) [9] with dictionary learning, which exhibits runaway in the absence of an effective normalization procedure [15].

Original languageEnglish
Title of host publicationProceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference, NICE 2022
PublisherAssociation for Computing Machinery
Pages58-60
Number of pages3
ISBN (Electronic)9781450395595
DOIs
StatePublished - 28 Mar 2022
Externally publishedYes
Event2022 Annual Neuro-Inspired Computational Elements Conference, NICE 2022 - Virtual, Online, United States
Duration: 28 Mar 20221 Apr 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2022 Annual Neuro-Inspired Computational Elements Conference, NICE 2022
Country/TerritoryUnited States
CityVirtual, Online
Period28/03/221/04/22

Keywords

  • Hebbian learning
  • synaptic saturation
  • synaptic stability
  • synfire-gated synfire chains

Fingerprint

Dive into the research topics of 'A Neuromorphic Normalization Algorithm for Stabilizing Synaptic Weights with Application to Dictionary Learning in LCA'. Together they form a unique fingerprint.

Cite this