Feature extraction using spiking convolutional neural networks

Ruthvik Vaila, John Chiasson, Vishal Saxena

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

16 Scopus citations

Abstract

Spiking neural networks are biologically plausible counterparts of the artificial neural networks. Conventional (non spiking) artificial neural networks are trained using a stochastic gradient descent algorithm (back propagation) while spiking neural networks are trained using the spike timing dependant plasticity algorithm. Training conventional neural networks is a memory and computationally/energy intensive job. Spiking networks show the potential to reduce both memory and energy usage. In this work, we consider spiking neural networks (SNN) as a classifier of the MNIST and NMNIST digits. We compare SNNs with convolutional neural networks in terms of classification accuracy, catastrophic forgetting.

Original languageEnglish
Title of host publicationICONS 2019 - Proceedings of International Conference on Neuromorphic Systems
ISBN (Electronic)9781450376808
DOIs
StatePublished - 23 Jul 2019
Event2019 International Conference on Neuromorphic Systems, ICONS 2019 - Knoxville, United States
Duration: 23 Jul 201925 Jul 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2019 International Conference on Neuromorphic Systems, ICONS 2019
Country/TerritoryUnited States
CityKnoxville
Period23/07/1925/07/19

Keywords

  • Catastrophic forgetting
  • Datasets
  • Feature extraction
  • Neural networks
  • R-STDP
  • STDP

Fingerprint

Dive into the research topics of 'Feature extraction using spiking convolutional neural networks'. Together they form a unique fingerprint.

Cite this