CRBA: A Competitive Rate-Based Algorithm Based on Competitive Spiking Neural Networks

In this paper we present a Competitive Rate-Based Algorithm (CRBA) that approximates operation of a Competitive Spiking Neural Network (CSNN). CRBA is based on modeling of the competition between neurons during a sample presentation, which can be reduced to ranking of the neurons based on a dot prod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in computational neuroscience Jg. 15; S. 627567
Hauptverfasser: Cachi, Paolo G., Ventura, Sebastián, Cios, Krzysztof J.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Research Foundation 22.04.2021
Frontiers Media S.A
Schlagworte:
Algorithms
Back propagation
Competition
competitive learning
competitive spiking neural networks
Computers
Fashion models
Firing pattern
Learning
MNIST
Neural networks
Neurons
Neuroscience
rate-based algorithm
unsupervised image classification
MNIST
competitive learning
competitive spiking neural networks
rate-based algorithm
unsupervised image classification
ISSN:1662-5188, 1662-5188
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper we present a Competitive Rate-Based Algorithm (CRBA) that approximates operation of a Competitive Spiking Neural Network (CSNN). CRBA is based on modeling of the competition between neurons during a sample presentation, which can be reduced to ranking of the neurons based on a dot product operation and the use of a discrete Expectation Maximization algorithm; the latter is equivalent to the spike time-dependent plasticity rule. CRBA's performance is compared with that of CSNN on the MNIST and Fashion-MNIST datasets. The results show that CRBA performs on par with CSNN, while using three orders of magnitude less computational time. Importantly, we show that the weights and firing thresholds learned by CRBA can be used to initialize CSNN's parameters that results in its much more efficient operation.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Reviewed by: Thomas Pfeil, Bosch Center for Artificial Intelligence, Germany; Aditya Gilra, Institute of Science and Technology Austria (IST Austria), Austria
Edited by: Anthony N. Burkitt, The University of Melbourne, Australia
ISSN:1662-5188
1662-5188
DOI:10.3389/fncom.2021.627567