Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies

Vahid Saranirad, Shirin Dora, T.Martin McGinnity, Damien Coyle

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

1 Citation (SciVal)
20 Downloads (Pure)

Abstract

Spiking Neural Networks (SNNs), An alternative to sigmoidal neural networks, include time into their operations using discrete signals called spikes. Employing spikes enables SNNs to mimic any feedforward sigmoidal neural network with lower power consumption. Recently a new type of SNN has been introduced for classification problems, known as Degree of Belonging SNN (DoB-SNN). DoB-SNN is a two-layer spiking neural network that shows significant potential as an alternative SNN architecture and learning algorithm. This paper introduces a new variant of Spike-Timing Dependent Plasticity (STDP), which is based on the assembly of neurons and expands the DoB-SNN's training algorithm for multilayer architectures. The new learning rule, known as assembly-based STDP, employs trained DoBs in each layer to train the next layer and build strong connections between neurons from the same assembly while creating inhibitory connections between neurons from different assemblies in two consecutive layers. The performance of the multilayer DoB-SNN is evaluated on five datasets from the UCI machine learning repository. Detailed comparisons on these datasets with other supervised learning algorithms show that the multilayer DoB-SNN can achieve better performance on 4/5 datasets and comparable performance on 5th when compared to multilayer algorithms that employ considerably more trainable parameters.
Original languageEnglish
Title of host publication2022 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationUnited States
Publisher IEEE Transactions on Medical Imaging
Pages1-7
Number of pages7
ISBN (Electronic)978-1-7281-8671-9
ISBN (Print)978-1-6654-9526-4
DOIs
Publication statusPublished - 30 Sept 2022

Publication series

NameInternational Joint Conference on Neural Networks (IJCNN)
PublisherIEEE
ISSN (Print)2161-4393
ISSN (Electronic)2161-4407

Bibliographical note

Funding Information: ACKNOWLEDGMENT This project was supported by Dr George Moore PhD scholarship in intelligent data analytics. We are grateful for access to the Tier 2 High Performance Computing resources provided by the Northern Ireland High Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant No. EP/T022175. Damien Coyle is grateful for funding UKRI Turing AI Fellowship 2021-2025 funded by the EPSRC (grant number EP/V025724/1).

Keywords

  • STDP
  • assembly of neurons
  • DoB
  • degree of belonging
  • spiking neural network
  • SNN

Fingerprint

Dive into the research topics of 'Assembly-based STDP: A New Learning Rule for Spiking Neural Networks Inspired by Biological Assemblies'. Together they form a unique fingerprint.

Cite this