A matrix method for optimizing a neural network

Authors:
Simon A. Barton
Affiliations:
Defence Research Establishment Suffield, Box 4000, Medicine Hat, Alberta, T1A 8K6, Canada
Venue:
Neural Computation
Year:
1991

Citing 4
Cited 1

Neural computing: theory and practice

Neural computing: theory and practice
The upstart algorithm: a method for constructing and training feedforward neural networks

Neural Computation
Layered neural networks with Gaussian hidden units as universal approximations

Neural Computation
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Comparative analysis of genetic algorithm, simulated annealing and cutting angle method for artificial neural networks

MLDM'05 Proceedings of the 4th international conference on Machine Learning and Data Mining in Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

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.