It is shown theoretically that for an arbitrary T-element training set with t(t⩽T) different inputs, the backpropagation error surface does not have suboptimal local minima if the network is capable of exactly implementing an arbitrary training set consisting of t different patterns. As a special case, the error surface of a backpropagation network with one hidden layer and t-1 hidden units has no local minima, if the network is trained by an arbitrary T-element set with t different inputs
Published in:
Neural Networks, IEEE Transactions on
(Volume:3
,
Issue:
6
)
Date of Publication:
Nov 1992
- Page(s):
-
1019
-
1021
- ISSN :
-
1045-9227
- INSPEC Accession Number:
-
4322845
- Digital Object Identifier :
-
10.1109/72.165604
- Product Type:
-
Journals & Magazines
- Date of Current Version :
-
06 August 2002
- Issue Date :
-
Nov 1992
- Sponsored by :
-
IEEE Computational Intelligence Society