DocumentCode
2727207
Title
Backpropagation converges for multi-layered networks and linearly-separable patterns
Author
Gori, Marco ; Tesi, A.
Author_Institution
Dipartimento di Sistemi e Inf., Firenze Univ.
fYear
1991
fDate
8-14 Jul 1991
Abstract
Summary form only given. Backpropagation can fail to discover the optimal solution, since it can get stuck in local minima. In this paper it is proved that it converges provided that the patterns are linearly separable. This is also true for networks with hidden units. In this case, the experience gained in several experiments shows that multilayered networks surpass perceptrons in generalization to new examples
Keywords
convergence; learning systems; neural nets; optimisation; backpropagation; generalization; hidden units; linearly-separable patterns; multilayered networks; optimal solution; Backpropagation; Multilayer perceptrons;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location
Seattle, WA
Print_ISBN
0-7803-0164-1
Type
conf
DOI
10.1109/IJCNN.1991.155475
Filename
155475
Link To Document