Dynamically Evolving Spiking Neural network for pattern recognition

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

1 Citation (Scopus)

Abstract

This paper presents a novel RBF-like fast dynamically Evolving Spiking Neural classifier (ESNC). The trained feed-forward SNN consists of three layers of spiking neurons: an encoding layer which temporally encodes real valued features into spatio-temporal spike patterns, a hidden layer of dynamically grown and pruned neurons which perform spatiotemporal clustering, and an evolving output layer for classification. Both the structure and weights of the SNN are learned dynamically through a combination of unsupervised and supervised learning paradigms. An unsupervised clustering method is implemented by the hidden layer for adjusting the synaptic weights of the hidden neurons afferent connections. The centre of each hidden RBF neuron is represented by a vector of temporal distances between the first spike of the hidden neuron and the presynaptic spikes. In addition, strategies are proposed to adjust the structure of the hidden and output layers as inputs are presented to the SNN, and classification at the output layer is achieved through supervised learning where a learning window is used to adjust the weights of the output neurons afferent connections. The proposed learning algorithm is demonstrated on several benchmark datasets from the UCL machine learning repository. The results show comparable performance with existing machine learning algorithms and demonstrate the ability of the proposed algorithm to learn incoming data samples in a hybrid way and in one epoch only.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages8
DOIs
Publication statusPublished - Jul 2015
EventInternational Joint Conference on Neural Networks (IJCNN) - Ireland
Duration: 1 Jul 2015 → …

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN)
Period1/07/15 → …

Fingerprint

Neurons
Pattern recognition
Neural networks
Supervised learning
Learning algorithms
Learning systems
Unsupervised learning
Classifiers

Keywords

  • adaptive spiking neural networks
  • classification
  • clustering
  • spiking neurons

Cite this

@inproceedings{482ba56863d247dcb4b47ffe665747a2,
title = "Dynamically Evolving Spiking Neural network for pattern recognition",
abstract = "This paper presents a novel RBF-like fast dynamically Evolving Spiking Neural classifier (ESNC). The trained feed-forward SNN consists of three layers of spiking neurons: an encoding layer which temporally encodes real valued features into spatio-temporal spike patterns, a hidden layer of dynamically grown and pruned neurons which perform spatiotemporal clustering, and an evolving output layer for classification. Both the structure and weights of the SNN are learned dynamically through a combination of unsupervised and supervised learning paradigms. An unsupervised clustering method is implemented by the hidden layer for adjusting the synaptic weights of the hidden neurons afferent connections. The centre of each hidden RBF neuron is represented by a vector of temporal distances between the first spike of the hidden neuron and the presynaptic spikes. In addition, strategies are proposed to adjust the structure of the hidden and output layers as inputs are presented to the SNN, and classification at the output layer is achieved through supervised learning where a learning window is used to adjust the weights of the output neurons afferent connections. The proposed learning algorithm is demonstrated on several benchmark datasets from the UCL machine learning repository. The results show comparable performance with existing machine learning algorithms and demonstrate the ability of the proposed algorithm to learn incoming data samples in a hybrid way and in one epoch only.",
keywords = "adaptive spiking neural networks, classification, clustering, spiking neurons",
author = "Jinling Wang and Ammar Belatreche and Liam Maguire and T.Martin McGinnity",
year = "2015",
month = "7",
doi = "10.1109/IJCNN.2015.7280649",
language = "English",
booktitle = "Unknown Host Publication",

}

Wang, J, Belatreche, A, Maguire, L & McGinnity, TM 2015, Dynamically Evolving Spiking Neural network for pattern recognition. in Unknown Host Publication. International Joint Conference on Neural Networks (IJCNN), 1/07/15. https://doi.org/10.1109/IJCNN.2015.7280649

Dynamically Evolving Spiking Neural network for pattern recognition. / Wang, Jinling; Belatreche, Ammar; Maguire, Liam; McGinnity, T.Martin.

Unknown Host Publication. 2015.

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

TY - GEN

T1 - Dynamically Evolving Spiking Neural network for pattern recognition

AU - Wang, Jinling

AU - Belatreche, Ammar

AU - Maguire, Liam

AU - McGinnity, T.Martin

PY - 2015/7

Y1 - 2015/7

N2 - This paper presents a novel RBF-like fast dynamically Evolving Spiking Neural classifier (ESNC). The trained feed-forward SNN consists of three layers of spiking neurons: an encoding layer which temporally encodes real valued features into spatio-temporal spike patterns, a hidden layer of dynamically grown and pruned neurons which perform spatiotemporal clustering, and an evolving output layer for classification. Both the structure and weights of the SNN are learned dynamically through a combination of unsupervised and supervised learning paradigms. An unsupervised clustering method is implemented by the hidden layer for adjusting the synaptic weights of the hidden neurons afferent connections. The centre of each hidden RBF neuron is represented by a vector of temporal distances between the first spike of the hidden neuron and the presynaptic spikes. In addition, strategies are proposed to adjust the structure of the hidden and output layers as inputs are presented to the SNN, and classification at the output layer is achieved through supervised learning where a learning window is used to adjust the weights of the output neurons afferent connections. The proposed learning algorithm is demonstrated on several benchmark datasets from the UCL machine learning repository. The results show comparable performance with existing machine learning algorithms and demonstrate the ability of the proposed algorithm to learn incoming data samples in a hybrid way and in one epoch only.

AB - This paper presents a novel RBF-like fast dynamically Evolving Spiking Neural classifier (ESNC). The trained feed-forward SNN consists of three layers of spiking neurons: an encoding layer which temporally encodes real valued features into spatio-temporal spike patterns, a hidden layer of dynamically grown and pruned neurons which perform spatiotemporal clustering, and an evolving output layer for classification. Both the structure and weights of the SNN are learned dynamically through a combination of unsupervised and supervised learning paradigms. An unsupervised clustering method is implemented by the hidden layer for adjusting the synaptic weights of the hidden neurons afferent connections. The centre of each hidden RBF neuron is represented by a vector of temporal distances between the first spike of the hidden neuron and the presynaptic spikes. In addition, strategies are proposed to adjust the structure of the hidden and output layers as inputs are presented to the SNN, and classification at the output layer is achieved through supervised learning where a learning window is used to adjust the weights of the output neurons afferent connections. The proposed learning algorithm is demonstrated on several benchmark datasets from the UCL machine learning repository. The results show comparable performance with existing machine learning algorithms and demonstrate the ability of the proposed algorithm to learn incoming data samples in a hybrid way and in one epoch only.

KW - adaptive spiking neural networks

KW - classification

KW - clustering

KW - spiking neurons

U2 - 10.1109/IJCNN.2015.7280649

DO - 10.1109/IJCNN.2015.7280649

M3 - Conference contribution

BT - Unknown Host Publication

ER -