A Suppression-based STDP Rule Resilient to Jitter Noise in Spike Patterns for Neuromorphic Computing

Ashish Gautam, Takashi Kohno, Prasanna Date, Robert Patton, Thomas Potok

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

Abstract

Multi-spike models of synaptic plasticity, such as the triplet and suppression spike-timing-dependent plasticity (STDP) rules, exhibit better alignment with neurophysiological data in the brain compared to the pair-based STDP rule. Previous studies have empirically shown that the pair-based STDP rule can detect spatiotemporal spike patterns hidden in equally dense distractor spike trains in an unsupervised manner. However, it fails to detect spike patterns influenced by jitter noise. Given that spiking neural networks (SNNs) exhibit variability in generated spike trains in response to the same inputs, it becomes imperative to have learning rules capable of detecting spike patterns even in the presence of jitter noise. In this study, we introduce a simplified suppression-based STDP rule that demonstrates significantly enhanced tolerance to jitter in spike patterns compared to the pair-based STDP rule. Unlike the ideal suppression STDP rule, characterized by an exponential learning window and requiring high-resolution synapses, the simplified rule limits the synaptic efficacy update to a single bit at any given instant. Moreover, it employs 4-bit fixed-point synapses, facilitating straightforward implementation in neuromorphic hardware.

Original languageEnglish
Title of host publicationProceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages209-216
Number of pages8
ISBN (Electronic)9798350368659
DOIs
StatePublished - 2024
Event2024 International Conference on Neuromorphic Systems, ICONS 2024 - Arlington, United States
Duration: Jul 30 2024Aug 2 2024

Publication series

NameProceedings - 2024 International Conference on Neuromorphic Systems, ICONS 2024

Conference

Conference2024 International Conference on Neuromorphic Systems, ICONS 2024
Country/TerritoryUnited States
CityArlington
Period07/30/2408/2/24

Keywords

  • jitter noise
  • lateral inhibition
  • low-resolution synapse
  • Multi-spike STDP model
  • neuromorphic computing
  • spike pattern detection
  • suppression STDP rule
  • Triplet STDP rule

Fingerprint

Dive into the research topics of 'A Suppression-based STDP Rule Resilient to Jitter Noise in Spike Patterns for Neuromorphic Computing'. Together they form a unique fingerprint.

Cite this