DocumentCode :
2324184
Title :
Synthesis of sigma-pi neural networks by the breeder genetic programming
Author :
Zhang, Byoung-Tak ; Muhlenbein, Heinz
Author_Institution :
German Nat. Res. Center for Comput. Sci., St. Augustin, Germany
fYear :
1994
fDate :
27-29 Jun 1994
Firstpage :
318
Abstract :
Genetic programming has been successfully applied to evolve computer programs for solving a variety of interesting problems. The breeder genetic programming (BGP) method has Occam´s razor in its fitness measure to evolve minimal size multilayer perceptrons. In this paper, we apply the method to synthesis of sigma-pi neural networks. Unlike perceptron architectures, sigma-pi networks use product units as well as summation units to build higher-order terms. The effectiveness of the method is demonstrated on benchmark problems. Simulation results on noisy data suggest that BGP not only improves the generalization performance, but it can also accelerate the convergence speed
Keywords :
convergence; genetic algorithms; neural nets; nonlinear network synthesis; programming; Occam´s razor; benchmark problems; breeder genetic programming; computer program evolution; convergence speed; fitness measure; generalization performance; higher-order terms; minimal size multilayer perceptrons; noisy data; product units; sigma-pi neural network synthesis; simulation; summation units; Acceleration; Artificial intelligence; Computational modeling; Convergence; Genetic programming; Multi-layer neural network; Multilayer perceptrons; Network synthesis; Neural networks; Size measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
Type :
conf
DOI :
10.1109/ICEC.1994.349933
Filename :
349933
Link To Document :
بازگشت