DocumentCode
1621303
Title
Error functions, error signals, and conjugate gradient back propagation
Author
Lister, R. ; Stone, J.V.
Author_Institution
Queensland Univ. of Technol., Brisbane, Qld., Australia
fYear
1995
Firstpage
76
Lastpage
81
Abstract
We propose a three class taxonomy of error functions, based on the limit behaviour of the error signal. We classify four established error functions: the quadratic, Fahlman´s Quickprop, entropy, and the exception error function. We introduce two new error functions, and benchmark all six on the N-2-N encoder. The two new functions found correct solutions faster and more reliably than the established functions
Keywords
backpropagation; conjugate gradient methods; error analysis; multilayer perceptrons; Quickprop; conjugate gradient back propagation; entropy function; error functions; error signals; exception error function; limit behaviour; quadratic function;
fLanguage
English
Publisher
iet
Conference_Titel
Artificial Neural Networks, 1995., Fourth International Conference on
Conference_Location
Cambridge
Print_ISBN
0-85296-641-5
Type
conf
DOI
10.1049/cp:19950532
Filename
497794
Link To Document