Title :
Search for new learning rules for cellular neural networks using genetic programming
Author :
Radwan, E. ; Tazaki, E.
Author_Institution :
Dept. of Control & Syst. Eng., Tom Univ. of Yokohama, Japan
Abstract :
We propose a new technique based upon genetic programming to discover new learning rules for cellular neural networks. We choose genetic programming not only for its ability to discover the values of rule parameter but also for its ability to discover the optimal number of parameters and the form of the rules. A new supervised learning algorithm has been discovered and comparison with other different methods is taken into account.
Keywords :
cellular neural nets; genetic algorithms; learning (artificial intelligence); cellular neural network; genetic programming; rule parameter discovery; supervised learning algorithm;
Conference_Titel :
SICE 2004 Annual Conference
Conference_Location :
Sapporo
Print_ISBN :
4-907764-22-7
