Title :
Back error propagation - A critique
Author_Institution :
ESL Inc., Sunnyvale, CA, USA
fDate :
Feb. 29 1988-March 3 1988
Abstract :
A neural-net algorithm known as back error propagation (BEP) is described and critiqued. A generic black-box view is presented, followed by a description of several noteworthy experiments. A review of the learning algorithm is given with a critique. Some training tips are offered along with a few variations on the basic design. A possible trend in neural net evolution is discussed, suggesting that the BEP could be heading toward a genetic dead end, despite early successes in small-scale experiments.<>
Keywords :
learning systems; neural nets; back error propagation; black-box view; learning algorithm; neural-net algorithm; training tips; Artificial neural networks; Computer architecture; Cybernetics; Genetics; Intelligent systems; Minimax techniques; Neural networks; Pattern recognition; Predictive models; Signal processing algorithms;
Conference_Titel :
Compcon Spring '88. Thirty-Third IEEE Computer Society International Conference, Digest of Papers
Conference_Location :
San Francisco, CA, USA
Print_ISBN :
0-8186-0828-5
DOI :
10.1109/CMPCON.1988.4895
