String Pattern Recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization

String Kernels - Text Classification - Evolving Spiking Neural Network - Particle Swarm - Quantum Computing

This paper presents a novel method for string classification using ESNN-QiPSO. The experiments have shown that ESNN with parameter optimization and using a small number of features produces promising results that is significant for future exploration.  Other work includes how to find a more effective method for choosing the most relevant features and eliminating irrelevant features.

This paper proposes a novel method for string pattern recognition using an Evolving Spiking Neural Network (ESNN) with Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals an interesting concept of QiPSO by representing information as binary structures. The mechanism optimizes the ESNN parameters and relevant features using the wrapper approach simultaneously. The N-gram kernel is used to map Reuters string datasets into high dimensional feature matrix which acts as an input to the proposed method. The results show promising string classification results as well as satisfactory QiPSO performance in obtaining the best combination of ESNN parameters and in identifying the most relevant features.