Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

Fall 1991, Vol. 3, No. 3, Pages 450-459
(doi: 10.1162/neco.1991.3.3.450)
© 1991 Massachusetts Institute of Technology
A Matrix Method for Optimizing a Neural Network
Article PDF (390.73 KB)
Abstract

A matrix method is described that optimizes the set of weights and biases for the output side of a network with a single hidden layer of neurons, given any set of weights and biases for the input side of the hidden layer. All the input patterns are included in a single optimization cycle. A simple iterative minimization procedure is used to optimize the weights and biases on the input side of the hidden layer. Many test problems have been solved, confirming the validity of the method. The results suggest that for a network with a single layer of hidden sigmoidal nodes, the accuracy of a functional representation is reduced as the nonlinearity of the function increases.