© The Institution of Electrical Engineers
A fast learning algorithm for feedforward neural networks is described. This algorithm is based on modifications to the backpropagation algorithm. The learning rate and momentum coefficient are adapted according to the coefficient of correlation between the downhill gradient and the previous weight update.
References
-
-
1)
-
L.B. Almeida ,
F.M. Silva
.
(1990)
Acceleration techniques for the backpropagation algorithm, Lectures notes in computer science.
-
2)
-
Special Issue on intelligent control.
Int. J. Contr.
-
3)
-
D.E. Rumelhart ,
G.E. Hinton ,
R.J. Williams ,
D.E. Rumelhart ,
J.L. McClelland
.
(1986)
Learning internal representations by error back propagation, Parallel distributed processing: Explorations in the microstruture of cognition.
-
4)
-
B. Widrow ,
M.A. Lehr
.
30 years of adaptive neural networks: Perceptron, Madaline and backpropagation.
Proc. IEE
,
9 ,
1415 -
1442
http://iet.metastore.ingenta.com/content/journals/10.1049/el_19931131
Related content
content/journals/10.1049/el_19931131
pub_keyword,iet_inspecKeyword,pub_concept
6
6