The Enhancement of Evolving Spiking Neural Network with Dynamic Population Particle Swarm Optimization

Abstract

This study presents an integration of Evolving Spiking Neural - Network (ESNN) with Dynamic Population Particle Swarm Optimization (DPPSO). The original ESNN framework does not automatically modulate its parameters’ optimum values. Thus, an integrated framework is proposed to optimize ESNN parameters namely, the modulation factor (mod), similarity factor (sim), and threshold factor (c). DPPSO improves the original PSO technique by implementing a dynamic particle population. Performance analysis is measured on classification accuracy in comparison with the existing methods. Five datasets retrieved from UCI machine learning are selected to simulate the classification problem. The proposed framework improves ESNN performance in regulating its parameters’ optimum values.