Universiti Teknologi Malaysia Institutional Repository

Integrated feature selection and parameter optimization for evolving spiking neutral networks using quantum inspired particle swarm optimization

Abdull Hamed, Haza Nuzly and Kasabov, Nikola and Shamsuddin, Siti Mariyam (2009) Integrated feature selection and parameter optimization for evolving spiking neutral networks using quantum inspired particle swarm optimization. In: International Conference of Soft Computing and Pattern Recognition 2009 (SoCPaR 2009), 2009, Malacca, Malaysia .

[img]
Preview
PDF
65Kb

Official URL: http://dx.doi.org/10.1109/SoCPaR.2009.139

Abstract

This paper proposes a novel method for optimizing features and parameters in the Evolving Spiking Neural Network (ESNN) using Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals the interesting concept of QiPSO in which information is represented as binary structures. The mechanism simultaneously optimizes the ESNN parameters and relevant features using wrapper approach. A synthetic dataset is used to evaluate the performance of the proposed method. The results show that QiPSO yields promising outcomes in obtaining the best combination of ESNN parameters as well as in identifying the most relevant features.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:evolving spiking neural network, feature optimization, parameter optimization, particle swarm, quantum computing
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:16202
Deposited By: Liza Porijo
Deposited On:20 Oct 2011 09:45
Last Modified:20 Oct 2011 09:45

Repository Staff Only: item control page