Title :
An evolutionary method for the design of generic neural networks
Author :
Edwards, David ; Brown, Keith ; Taylor, Nick
Author_Institution :
Dept. of Comput. & Electr. Eng., Heriot-Watt Univ., Edinburgh, UK
fDate :
6/24/1905 12:00:00 AM
Abstract :
Hybrid systems using evolution to optimize neural network design or training are usually limited in scope and effectiveness. A system is presented that permits the widest variety of networks to be evolved using a two-stage GA approach. Networks generated for a benchmark machine learning task compare favourably with alternative methods
Keywords :
genetic algorithms; learning (artificial intelligence); neural nets; evolutionary method; generic neural networks; machine learning task; two-stage genetic algorithm approach; Computer networks; Design methodology; Design optimization; Encoding; Genetic mutations; Hybrid intelligent systems; Intelligent networks; Machine learning; Neural networks; Optimization methods;
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.2002.1004510
