Back error propagation - A critique

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 va...

Full description

Saved in:
Bibliographic Details
Published inCOMPCON Spring '88: 33rd IEEE Computer Society International Conference pp. 387 - 392
Main Author Jurik, M.
Format Conference Proceeding
LanguageEnglish
Published IEEE Comput. Soc. Press 1988
Subjects
Artificial neural networks
Computer architecture
Cybernetics
Genetics
Intelligent systems
Minimax techniques
Neural networks
Pattern recognition
Predictive models
Signal processing algorithms
Online AccessGet full text
ISBN0818608285
9780818608285
DOI10.1109/CMPCON.1988.4895

Cover

More Information
Summary: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.< >
ISBN:0818608285
9780818608285
DOI:10.1109/CMPCON.1988.4895