ML Anthology

Universal Approximation of Multiple Nonlinear Operators by Neural Networks

Andrew D. Back, Tianping Chen
NeCo 2002 pp. 2561-2566
doi:10.1162/089976602760407964 /neco/2002/back2002neco-universal/

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.

NeCo Semantic Scholar

Cite

Text

Back and Chen. "Universal Approximation of Multiple Nonlinear Operators by Neural Networks." Neural Computation, 2002. doi:10.1162/089976602760407964

Markdown

[Back and Chen. "Universal Approximation of Multiple Nonlinear Operators by Neural Networks." Neural Computation, 2002.](https://mlanthology.org/neco/2002/back2002neco-universal/) doi:10.1162/089976602760407964

BibTeX

@article{back2002neco-universal,
  title     = {{Universal Approximation of Multiple Nonlinear Operators by Neural Networks}},
  author    = {Back, Andrew D. and Chen, Tianping},
  journal   = {Neural Computation},
  year      = {2002},
  pages     = {2561-2566},
  doi       = {10.1162/089976602760407964},
  volume    = {14},
  url       = {https://mlanthology.org/neco/2002/back2002neco-universal/}
}