Multi-Objective Differential Evolution of Evolving Spiking Neural Networks for Classification Problems

Abstract : Spiking neural network (SNN) plays an essential role in classification problems. Although there are many models of SNN, Evolving Spiking Neural Network (ESNN) is widely used in many recent research works. Evolutionary algorithms, mainly differential evolution (DE) have been used for enhancing ESNN algorithm. However, many real-world optimization problems include several contradictory objectives. Rather than single optimization, Multi- Objective Optimization (MOO) can be utilized as a set of optimal solutions to solve these problems. In this paper, MOO is used in a hybrid learning of ESNN to determine the optimal pre-synaptic neurons (network structure) and accuracy performance for classification problems simultaneously. Standard data sets from the UCI machine learning are used for evaluating the performance of this multi objective hybrid model. The experimental results have proved that the multi-objective hybrid of Differential Evolution with Evolving Spiking Neural Network (MODE-ESNN) gives better results in terms of accuracy and network structure.
Type de document :
Communication dans un congrès
Richard Chbeir; Yannis Manolopoulos; Ilias Maglogiannis; Reda Alhajj. 11th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI 2015), Sep 2015, Bayonne, France. IFIP Advances in Information and Communication Technology, AICT-458, pp.351-368, 2015, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-319-23868-5_25〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01385370
Contributeur : Hal Ifip <>
Soumis le : vendredi 21 octobre 2016 - 11:43:50
Dernière modification le : vendredi 1 décembre 2017 - 01:16:45

Fichier

978-3-319-23868-5_25_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Abdulrazak Saleh, Siti Shamsuddin, Haza Hamed. Multi-Objective Differential Evolution of Evolving Spiking Neural Networks for Classification Problems. Richard Chbeir; Yannis Manolopoulos; Ilias Maglogiannis; Reda Alhajj. 11th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI 2015), Sep 2015, Bayonne, France. IFIP Advances in Information and Communication Technology, AICT-458, pp.351-368, 2015, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-319-23868-5_25〉. 〈hal-01385370〉

Partager

Métriques

Consultations de la notice

225

Téléchargements de fichiers

23