A New Learning Algorithm for Adaptive Spiking Neural Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a ’virtual’ supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages461-468
Number of pages8
Volume7062
DOIs
Publication statusPublished - 2011
EventInternational Conference on Neural Information Processing - China
Duration: 1 Jan 2011 → …

Conference

ConferenceInternational Conference on Neural Information Processing
Period1/01/11 → …

Fingerprint

Learning algorithms
Neurons
Neural networks

Cite this

Wang, Jinling ; Belatreche, Ammar ; Maguire, Liam ; McGinnity, Martin. / A New Learning Algorithm for Adaptive Spiking Neural Networks. Unknown Host Publication. Vol. 7062 2011. pp. 461-468
@inproceedings{6bd556ad392943fc88f856f2ef3cc48c,
title = "A New Learning Algorithm for Adaptive Spiking Neural Networks",
abstract = "This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a ’virtual’ supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.",
author = "Jinling Wang and Ammar Belatreche and Liam Maguire and Martin McGinnity",
year = "2011",
doi = "10.1007/978-3-642-24955-6_55",
language = "English",
volume = "7062",
pages = "461--468",
booktitle = "Unknown Host Publication",

}

Wang, J, Belatreche, A, Maguire, L & McGinnity, M 2011, A New Learning Algorithm for Adaptive Spiking Neural Networks. in Unknown Host Publication. vol. 7062, pp. 461-468, International Conference on Neural Information Processing, 1/01/11. https://doi.org/10.1007/978-3-642-24955-6_55

A New Learning Algorithm for Adaptive Spiking Neural Networks. / Wang, Jinling; Belatreche, Ammar; Maguire, Liam; McGinnity, Martin.

Unknown Host Publication. Vol. 7062 2011. p. 461-468.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A New Learning Algorithm for Adaptive Spiking Neural Networks

AU - Wang, Jinling

AU - Belatreche, Ammar

AU - Maguire, Liam

AU - McGinnity, Martin

PY - 2011

Y1 - 2011

N2 - This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a ’virtual’ supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.

AB - This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a ’virtual’ supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.

U2 - 10.1007/978-3-642-24955-6_55

DO - 10.1007/978-3-642-24955-6_55

M3 - Conference contribution

VL - 7062

SP - 461

EP - 468

BT - Unknown Host Publication

ER -