Title :
Evolutionary optimisation of evolving connectionist systems
Author :
Watts, Michael ; Kasabov, Nik
Author_Institution :
Dept. of Inf. Sci., Otago Univ., Dunedin, New Zealand
Abstract :
The paper presents a method for optimising parameter values of evolving connectionist systems (ECoS) for life-long learning. The method is based on evolutionary computation principles, and on genetic algorithms in particular. The method is illustrated on a spoken phoneme data classification task
Keywords :
circuit optimisation; evolutionary computation; learning (artificial intelligence); neural nets; signal classification; speech processing; evolutionary computation; evolutionary optimisation; evolving connectionist systems; genetic algorithms; life-long learning; parameter value optimisation; spoken phoneme data classification; Bioinformatics; Equations; Evolutionary computation; Gene expression; Genetic algorithms; Information retrieval; Information science; Neurons; Optimization methods; Predictive models;
Conference_Titel :
Evolutionary Computation, 2002. CEC '02. Proceedings of the 2002 Congress on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7282-4
DOI :
10.1109/CEC.2002.1006995
