DocumentCode
3250642
Title
Self-generating neural networks
Author
Wen, Wilson X. ; Liu, Huan ; Jennings, Andrew
Author_Institution
Telecom Res. Lab., Clayton, Vic., Australia
Volume
4
fYear
1992
fDate
7-11 Jun 1992
Firstpage
779
Abstract
A method for generating neural networks automatically is proposed. Not only the weights of the connections but also the structure of the network, including the number of neurons, the number of layers, and the interconnections among the neurons, is learned from the training examples. Issues of optimization and pruning of the generated networks are investigated. An experimental system has been implemented based on the proposed method and some experimental results and comparisons between this method and other methods are also given
Keywords
learning by example; optimisation; self-organising feature maps; generated networks; interconnections; layers; learning from examples; neurons; optimization; pruning; self-generating neural nets; weights; Artificial intelligence; Feedforward neural networks; Humans; Neural networks; Neurons; Resonance; Self-organizing networks; Telecommunications; Tree data structures; Tree graphs;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location
Baltimore, MD
Print_ISBN
0-7803-0559-0
Type
conf
DOI
10.1109/IJCNN.1992.227223
Filename
227223
Link To Document