Universal approximation of multiple nonlinear operators by neural networks

Authors:
Andrew D. Back;Tianping Chen
Affiliations:
Windale Technologies, Brisbane, QLD 4075, Australia;Department of Mathematics, Fudan University, Shanghai, 200433, China
Venue:
Neural Computation
Year:
2002

Citing 8
Cited 1

Multilayer feedforward networks are universal approximators

Neural Networks
Learning to control fast-weight memories: an alternative to dynamic recurrent networks

Neural Computation
Inductively inferring valid logical models of continuous-state dynamical systems

Theoretical Computer Science - Special issue on hybrid systems
Adaptive behavior form fixed weight networks

Information Sciences: an International Journal
Long short-term memory

Neural Computation
Complete memory structures for approximating nonlinear discrete-time mappings

IEEE Transactions on Neural Networks
Fixed-weight on-line learning

IEEE Transactions on Neural Networks
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems

IEEE Transactions on Neural Networks

Adaptive classification of temporal signals in fixed-weight recurrent neural networks: An existence proof

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, there has been interest in the observed capabilities of some classes of neural networks with fixed weights to model multiple nonlinear dynamical systems. While this property has been observed in simulations, open questions exist as to how this property can arise. In this article, we propose a theory that provides a possible mechanism by which this multiple modeling phenomenon can occur.