论文信息 - The Parameter Optimization of the Pulse Coupled Neural Network for the Pattern Recognition

The Parameter Optimization of the Pulse Coupled Neural Network for the Pattern Recognition

The pattern recognition using Pulse Coupled Neural Network (PCNN) had been proposed. In conventional studies, the parameters in the PCNN are used to be defined empirically and the optimization of parameters has been known as a remaining problem of PCNN. In this study, we show a method to apply the real coded genetic algorithm to the parameter optimization of the PCNN and we also show performances of pattern recognition by the PCNN with learned parameters.

Hiroaki Kurokawa | Masato Yonekawa | H. Kurokawa | Masato Yonekawa

[1] Reinhard Eckhorn,et al. Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

[2] Hiroaki Kurokawa,et al. An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation , 2009, ICANN.

[3] John L. Johnson,et al. PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[4] Xiaodong Gu,et al. Object Detection Using Unit-Linking PCNN Image Icons , 2006, ISNN.

[5] Jacek M. Zurada,et al. Advances in Neural Networks - ISNN 2006, Third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006, Proceedings, Part I , 2006, International Symposium on Neural Networks.

[6] Aapo Hyvärinen,et al. Learning Features by Contrasting Natural Images with Noise , 2009, ICANN.