Australian Journal of Intelligent Information Processing Systems, Vol 11, No 1 (2010): Neurodynamics

Font Size:  Small  Medium  Large

Probabilistic Evolving Spiking Neural Network Optimization Using Dynamic Quantum-inspired Particle Swarm Optimization

Haza Nuzly Abdull Hamed, Nikola Kasabov, Siti Mariyam Shamsuddin

Abstract


This paper proposes a novel Probabilistic Evolving Spiking Neural Network (PESNN) based on Kasabov’s
Probabilistic Neuron Model. The features, connections and parameters are optimized using Dynamic Quantum-
inspired Particle Swarm Optimization (DQiPSO). The features and connections are modeled as a quantum bit vector
while the parameter values are presented as real numbers. An improved search strategy is also being introduced to
probe the most relevant features and eliminate irrelevant ones. The proposed method is evaluated using a synthetic
dataset for classification problems. The results show that the proposed method is promising, with better accuracy and
capability to identify the most significant features while obtaining the best combination of PESNN’s connections and
parameters.

Full Text: PDF