TY - GEN
T1 - Self-Generating Neural Networks
AU - Wen, Wilson X.
AU - Liu, Huan
AU - Jennings, Andrew
N1 - Funding Information: The Permission of the Executive General Manager, TRL, to publish this paper is acknowledged. Publisher Copyright: © 1992 IEEE.
PY - 1992
Y1 - 1992
N2 - A method of generating neural networks automatically is proposed in this paper. 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 are all 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 our method and other methods are also given.
AB - A method of generating neural networks automatically is proposed in this paper. 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 are all 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 our method and other methods are also given.
UR - http://www.scopus.com/inward/record.url?scp=85132245121&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85132245121&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.1992.227211
DO - 10.1109/IJCNN.1992.227211
M3 - Conference contribution
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 850
EP - 855
BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Y2 - 7 June 1992 through 11 June 1992
ER -