Abstract
An algorithm for determining the optimal initial weights of feedforward neural networks based on linear algebraic methods is presented. With the optimal initial weights, the initial network error is enormous smaller. In one of the examples presented in this letter, the achieved accuracy is sufficient for direct application. If further smaller network error is required, the networks can be trained using backpropagation algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
W.H.Joerding, J.L.Meador. Encoding a Priori Information in Feedforward Networks,Neural Networks, vol. 4, pp. 847–856, 1991
N.Weymaere, J.P.Martens. Neural network classifiers under changing a priori conditions,Electronics Letters, vol. 29, no. 6, pp. 527–529, 18th March 1993.
G.H. Golub, C.F. Van Loan.Matrix Computations, John Hopkins Univ. Press, 1989.
A.N. Kolmogorov. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, [in Russian],Dokl. Akad. Nauk USSR, 114, pp. 953–956, 1957.
D.E.Rumelhart, G.E.Hinton, R.J.Williams. Learning internal representations by error backpropagation, in D.E.Rumelhart and J.L.McClelland eds.,Parallel Distributed Processings, MIT Press, Cambridge, Massachusetts, 1986.
F.Biegler-König, F.BÄrmann, A learning algorithm for multilayered neural networks based on linear least squares problems,Neural Networks, vol. 6, pp. 127–131, 1993.
M.C.Mackey and L.Glass, Oscillations and chaos in physiological control systems,Science, vol. 197, pp. 287–289, 1997.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yam, Y.F., Chow, T.W.S. Determining initial weights of feedforward neural networks based on least squares method. Neural Process Lett 2, 13–17 (1995). https://doi.org/10.1007/BF02312350
Issue Date:
DOI: https://doi.org/10.1007/BF02312350