An interclass margin maximization learning algorithm for evolving spiking neural network

This paper presents a new learning algorithm developed for a three layered spiking neural network for pattern classification problems. The learning algorithm maximizes the interclass margin and is referred to as the two stage margin maximization spiking neural network (TMM-SNN). In the structure lea...

Full description

Saved in:
Bibliographic Details
Main Authors: Dora, Shirin, Sundaram, Suresh, Sundararajan, Narasimhan
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/150435
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-150435
record_format dspace
spelling sg-ntu-dr.10356-1504352021-05-31T01:46:31Z An interclass margin maximization learning algorithm for evolving spiking neural network Dora, Shirin Sundaram, Suresh Sundararajan, Narasimhan School of Computer Science and Engineering Engineering::Computer science and engineering Classification Multilayer Network This paper presents a new learning algorithm developed for a three layered spiking neural network for pattern classification problems. The learning algorithm maximizes the interclass margin and is referred to as the two stage margin maximization spiking neural network (TMM-SNN). In the structure learning stage, the learning algorithm completely evolves the hidden layer neurons in the first epoch. Further, TMM-SNN updates the weights of the hidden neurons for multiple epochs using the newly developed normalized membrane potential learning rule such that the interclass margins (based on the response of hidden neurons) are maximized. The normalized membrane potential learning rule considers both the local information in the spike train generated by a presynaptic neuron and the existing knowledge (synaptic weights) stored in the network to update the synaptic weights. After the first stage, the number of hidden neurons and their parameters are not updated. In the output weights learning stage, TMM-SNN updates the weights of the output layer neurons for multiple epochs to maximize the interclass margins (based on the response of output neurons). Performance of TMM-SNN is evaluated using ten benchmark data sets from the UCI machine learning repository. Statistical performance comparison of TMM-SNN with other existing learning algorithms for SNNs is conducted using the nonparametric Friedman test followed by a pairwise comparison using the Fisher's least significant difference method. The results clearly indicate that TMM-SNN achieves better generalization performance in comparison to other algorithms. 2021-05-31T01:46:31Z 2021-05-31T01:46:31Z 2018 Journal Article Dora, S., Sundaram, S. & Sundararajan, N. (2018). An interclass margin maximization learning algorithm for evolving spiking neural network. IEEE Transactions On Cybernetics, 49(3), 989-999. https://dx.doi.org/10.1109/TCYB.2018.2791282 2168-2267 0000-0001-6182-4124 0000-0001-6275-0921 0000-0002-6972-8775 https://hdl.handle.net/10356/150435 10.1109/TCYB.2018.2791282 29994611 2-s2.0-85041003621 3 49 989 999 en IEEE Transactions on Cybernetics © 2018 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Classification
Multilayer Network
spellingShingle Engineering::Computer science and engineering
Classification
Multilayer Network
Dora, Shirin
Sundaram, Suresh
Sundararajan, Narasimhan
An interclass margin maximization learning algorithm for evolving spiking neural network
description This paper presents a new learning algorithm developed for a three layered spiking neural network for pattern classification problems. The learning algorithm maximizes the interclass margin and is referred to as the two stage margin maximization spiking neural network (TMM-SNN). In the structure learning stage, the learning algorithm completely evolves the hidden layer neurons in the first epoch. Further, TMM-SNN updates the weights of the hidden neurons for multiple epochs using the newly developed normalized membrane potential learning rule such that the interclass margins (based on the response of hidden neurons) are maximized. The normalized membrane potential learning rule considers both the local information in the spike train generated by a presynaptic neuron and the existing knowledge (synaptic weights) stored in the network to update the synaptic weights. After the first stage, the number of hidden neurons and their parameters are not updated. In the output weights learning stage, TMM-SNN updates the weights of the output layer neurons for multiple epochs to maximize the interclass margins (based on the response of output neurons). Performance of TMM-SNN is evaluated using ten benchmark data sets from the UCI machine learning repository. Statistical performance comparison of TMM-SNN with other existing learning algorithms for SNNs is conducted using the nonparametric Friedman test followed by a pairwise comparison using the Fisher's least significant difference method. The results clearly indicate that TMM-SNN achieves better generalization performance in comparison to other algorithms.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Dora, Shirin
Sundaram, Suresh
Sundararajan, Narasimhan
format Article
author Dora, Shirin
Sundaram, Suresh
Sundararajan, Narasimhan
author_sort Dora, Shirin
title An interclass margin maximization learning algorithm for evolving spiking neural network
title_short An interclass margin maximization learning algorithm for evolving spiking neural network
title_full An interclass margin maximization learning algorithm for evolving spiking neural network
title_fullStr An interclass margin maximization learning algorithm for evolving spiking neural network
title_full_unstemmed An interclass margin maximization learning algorithm for evolving spiking neural network
title_sort interclass margin maximization learning algorithm for evolving spiking neural network
publishDate 2021
url https://hdl.handle.net/10356/150435
_version_ 1702418248530657280