Universal Approximation of Multiple Nonlinear Operators by Neural Networks
- 1 November 2002
- journal article
- Published by MIT Press in Neural Computation
- Vol. 14 (11) , 2561-2566
- https://doi.org/10.1162/089976602760407964
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.Keywords
This publication has 13 references indexed in Scilit:
- Long Short-Term MemoryNeural Computation, 1997
- Adaptive behavior from fixed weight networksInformation Sciences, 1997
- Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systemsIEEE Transactions on Neural Networks, 1995
- Adaptation and learning using multiple models, switching, and tuningIEEE Control Systems, 1995
- Inductively inferring valid logical models of continuous-state dynamical systemsTheoretical Computer Science, 1995
- Approximations of continuous functionals by neural networks with application to dynamic systemsIEEE Transactions on Neural Networks, 1993
- Approximation theorems for discrete-time systemsIEEE Transactions on Circuits and Systems, 1991
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- STATE‐DEPENDENT MODELS: A GENERAL APPROACH TO NON‐LINEAR TIME SERIES ANALYSISJournal of Time Series Analysis, 1980