DocumentCode
2165500
Title
A possible genetic-algorithm based method for optimizing a class of ANN transfer functions
Author
Beddoess, Michael P. ; Ward, Rabab K.
Author_Institution
Dept. of Electr. & Comput. Eng., British Columbia Univ., Canada
Volume
2
fYear
2002
fDate
2002
Firstpage
1353
Abstract
This paper proposes a hybrid of two methods to determine the weight-constants in a class of artificial neuron networks, ANNs. The class of ANNs we are interested in are characterized by feed-forward processing elements. One of the methods is the genetic algorithm, GA; the other is "training through" back-propagation of the error, BPE. We expect our hybrid scheme to be faster than using BPE alone.
Keywords
backpropagation; feedforward neural nets; genetic algorithms; linear predictive coding; transfer functions; ANN transfer function optimization; artificial neuron networks; back-propagation error; feedforward processing elements; genetic algorithm; hybrid method; linear prediction coder; training; weight-constants; Artificial neural networks; Backpropagation; Circuits; Error correction; Genetics; Neurons; Optimization methods; Resource management; Transfer functions; Weight measurement;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on
Print_ISBN
0-7803-7503-3
Type
conf
DOI
10.1109/ICDSP.2002.1028345
Filename
1028345
Link To Document