A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks

Taherkhani, A ORCID: https://orcid.org/0000-0002-3627-6362, Belatreche, A, Li, Y and Maguire, LP, 2018. A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X

Preview

Text PubSub10605_Taherkhani.pdf - Post-print Download (2MB) | Preview

Abstract

There is a biological evidence to prove information is coded through precise timing of spikes in the brain. However, training a population of spiking neurons in a multilayer network to fire at multiple precise times remains a challenging task. Delay learning and the effect of a delay on weight learning in a spiking neural network (SNN) have not been investigated thoroughly. This paper proposes a novel biologically plausible supervised learning algorithm for learning precisely timed multiple spikes in a multilayer SNNs. Based on the spike-timing-dependent plasticity learning rule, the proposed learning method trains an SNN through the synergy between weight and delay learning. The weights of the hidden and output neurons are adjusted in parallel. The proposed learning method captures the contribution of synaptic delays to the learning of synaptic weights. Interaction between different layers of the network is realized through biofeedback signals sent by the output neurons. The trained SNN is used for the classification of spatiotemporal input patterns. The proposed learning method also trains the spiking network not to fire spikes at undesired times which contribute to misclassification. Experimental evaluation on benchmark data sets from the UCI machine learning repository shows that the proposed method has comparable results with classical rate-based methods such as deep belief network and the autoencoder models. Moreover, the proposed method can achieve higher classification accuracies than single layer and a similar multilayer SNN.

Item Type:	Journal article
Publication Title:	IEEE Transactions on Neural Networks and Learning Systems
Creators:	Taherkhani, A., Belatreche, A., Li, Y. and Maguire, L.P.
Publisher:	IEEE
Date:	1 March 2018
ISSN:	2162-237X
Identifiers:	Number Type 10.1109/TNNLS.2018.2797801 DOI
Rights:	This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/.
Divisions:	Schools > School of Science and Technology
Record created by:	Jill Tomkinson
Date Added:	20 Mar 2018 09:57
Last Modified:	20 Mar 2018 09:57
URI:	https://irep.ntu.ac.uk/id/eprint/33034

Actions (login required)

Edit View

Statistics

Views

Downloads