A multilayer neural network with piecewise-linear structure and back-propagation learning

1 May 1991

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks

Vol. 2 (3) , 395-403
https://doi.org/10.1109/72.97915

Abstract

A multilayer neural network which is given a two-layer piecewise-linear structure for every cascaded section is proposed. The neural networks have nonlinear elements that are neither sigmoidal nor of a signum type. Each nonlinear element is an absolute value operator. It is almost everywhere differentiable, which makes back-propagation feasible in a digital setting. Both the feedforward signal propagation and the backward coefficient update rules belong to the class of regular iterative algorithms. This form of neural network specializes in functional approximation and is anticipated to have applications in control, communications, and pattern recognition.

Keywords

This publication has 18 references indexed in Scilit:

Variants of self-organizing maps
IEEE Transactions on Neural Networks, 1990
Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification
IEEE Transactions on Neural Networks, 1990
Model-free distributed learning
IEEE Transactions on Neural Networks, 1990
A generalized canonical piecewise-linear representation
IEEE Transactions on Circuits and Systems, 1990
Adaptive nonlinear digital filter with canonical piecewise-linear structure
IEEE Transactions on Circuits and Systems, 1990
30 years of adaptive neural networks: perceptron, Madaline, and backpropagation
Proceedings of the IEEE, 1990
Layered neural nets for pattern recognition
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
Canonical piecewise-linear representation
IEEE Transactions on Circuits and Systems, 1988
Canonical piecewise-linear modeling
IEEE Transactions on Circuits and Systems, 1986
The escape behavior of the cockroachPeriplaneta americana
Journal of Comparative Physiology A, 1978