Publication Details

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

MICHLOVSKÝ Zbyněk. String Pattern Recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization. In: Neural Information Processing. Lecture Notes in Computer Science. Berlin / Heidelberg: Springer Verlag, 2009, pp. 611-619. ISBN 978-3-642-10682-8.
Czech title
Rozpoznávání vzorů řetězců s využitím Spiking Neural Networks and Quantum Inspired Particle Swarm optimalizace
Type
conference paper
Language
english
Authors
Michlovský Zbyněk, Ing. (DITS FIT BUT)
Keywords

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

Abstract

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.

Annotation

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.

Published
2009
Pages
611-619
Proceedings
Neural Information Processing
Series
Lecture Notes in Computer Science
Conference
ICONIP 2009 : 16th International Conference on Neural Information Processing , Bangkok, TH
ISBN
978-3-642-10682-8
Publisher
Springer Verlag
Place
Berlin / Heidelberg, DE
BibTeX
@INPROCEEDINGS{FITPUB9136,
   author = "Zbyn\v{e}k Michlovsk\'{y}",
   title = "String Pattern Recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization",
   pages = "611--619",
   booktitle = "Neural Information Processing",
   series = "Lecture Notes in Computer Science",
   year = 2009,
   location = "Berlin / Heidelberg, DE",
   publisher = "Springer Verlag",
   ISBN = "978-3-642-10682-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9136"
}
Back to top