Translator Disclaimer
Abstract
A new method, using genetic algorithms, for constructing a redundant unipolar interconnection weight matrix of the Interpattern Association model is presented. The global searching features of the genetic algorithms are adopted to help us avoiding too complicate procedures to complete a link search of using exhaustive search method. The upper bond and the lower bond of the searching links are adapted from the results of the maximum mode and the minimum mode of the RIPA model respectively. Computer simulation results show that the proposed genetic algorithms method not only has the features of accurate of constructing the IWM, but also has better network performance.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chii-Maw Uang, Yuan-Hsiu Yang, and Ching-Fen Jiang "Genetic algorithms-based unipolar IPA model", Proc. SPIE 4459, Photorefractive Fiber and Crystal Devices: Materials, Optical Properties, and Applications VII, and Optical Data Storage, (23 January 2002); https://doi.org/10.1117/12.454019
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Unipolar neural network using redundant interconnections
Proceedings of SPIE (December 07 1994)
Genetic-algorithm-based tri-state neural networks
Proceedings of SPIE (September 16 2002)
Fuzzy based IPA model
Proceedings of SPIE (January 23 2002)

Back to Top