Performance analysis of locally recurrent neural networks

Abstract

Many practical applications of neural networks require the identification of non‐linear deterministic systems or chaotic systems. In these cases the use of a network architecture known as locally recurrent neural network (LRNN) is often preferable in place of standard feedforward multi‐layer perceptron (MLP) networks, or of globally recurrent neural network. In this paper locally recurrent networks are used to simulate the behaviour of the Chua’s circuit that can be considered a paradigm for studying chaos. It is shown that such networks are able to identify the underlying link among the state variables of the Chua’s circuit. Moreover, they are able to behave like an autonomous Chua’s double scroll, showing a chaotic behaviour of the state variables obtainable through a suitable circuit elements choice.

Keywords

This publication has 16 references indexed in Scilit:

A unifying view of some training algorithms for multilayer perceptrons with FIR filter synapses
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Neural network identification of a nonlinear circuitmodel of hysteresis
Electronics Letters, 1997
Neural network modelling of variable hystereticinductors
Electronics Letters, 1996
Learning a simple recurrent neural state space model to behave like Chua's double scroll
IEEE Transactions on Circuits and Systems I: Regular Papers, 1995
Three steps to chaos. I. Evolution
IEEE Transactions on Circuits and Systems I: Regular Papers, 1993
FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
Neural Computation, 1991
Global optimization: a naive approach
IEEE Transactions on Circuits and Systems, 1990
Backpropagation through time: what it does and how to do it
Proceedings of the IEEE, 1990
Generalization of back-propagation to recurrent neural networks
Physical Review Letters, 1987
The double scroll family
IEEE Transactions on Circuits and Systems, 1986