Title: A hybrid differential evolution algorithm for parameter tuning of evolving spiking neural network
Authors: Abdulrazak Yahya Saleh; Siti Mariyam Shamsuddin; Haza Nuzly Abdull Hamed
Addresses: UTM Big Data Centre, Universiti Teknologi Malaysia (UTM), Skudai, 81310 Johor, Malaysia ' UTM Big Data Centre, Universiti Teknologi Malaysia (UTM), Skudai, 81310 Johor, Malaysia ' Soft Computing Research Group, Faculty of Computing, Universiti Teknologi Malaysia (UTM), Skudai, 81310 Johor, Malaysia
Abstract: In this paper, differential evolution (DE) has been utilised to solve the problem of tuning the parameters of evolving spiking neural network (ESNN) manually. As ESNN is sensitive to its parameters as other models, optimal integration of parameters leads to better classification accuracy. A hybrid differential evolution for parameter tuning of evolving spiking neural network (DEPT-ESNN) is presented for parameter optimisation for determining the optimal number of evolving spiking neural network (ESNN) parameters: modulation factor (Mod), similarity factor (Sim) and threshold factor (C). The best values of parameters are adaptively selected by differential evolution (DE) to avoid selecting suitable values for a particular problem by trial-and-error approach. Several standard datasets from UCI machine learning are used for evaluating the performance of this hybrid model. It has been found that the classification accuracy and other performance measures can be increased by using hybrid method with differential evolution DEPT_ESNN.
Keywords: differential evolution; evolving spiking neural networks; eSNN; parameter tuning; modulation factor; similarity factor; evolving SNNs; threshold factor.
International Journal of Computational Vision and Robotics, 2017 Vol.7 No.1/2, pp.20 - 34
Received: 28 Nov 2014
Accepted: 03 Feb 2015
Published online: 07 Dec 2016 *