Artificial neural networks as approximators of stochastic processes (1999)
| Venue: | Neural Networks |
BibTeX
@ARTICLE{Belli99artificialneural,
author = {M. R. Belli and M. Conti and S. Orcioni and C. Turchetti},
title = {Artificial neural networks as approximators of stochastic processes},
journal = {Neural Networks},
year = {1999},
volume = {12},
pages = {647--658}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the environment to determine decisions and subsequent actions to stimuli. By assuming that environment is essentially stochastic it follows that the mathematical framework for learning information from environment is the theory of stochastic processes approximation. The aim of this paper is to show that classes of neural networks capable of approximating stochastic processes exist. 1
Citations
| 1158 | Self-organization and associative memory - Kohonen - 1984 |
| 632 | Approximation by superposition’s of a sigmoidal function - Cybenko |
| 570 | Networks for approximation and learning - Poggio, Girosi - 1990 |
| 121 | Universal approximation using radial-basis-function networks - Park, Sandberg - 1991 |
| 22 | White X: Multilayer feed forward networks are universal approximations. Neural Net - Hornik, Stinchcomb - 1993 |
| 9 | Doob: Stochastic Processes - L - 1953 |
| 9 | Probability Theory - Prokhorov, Rozanov - 1970 |
| 6 | On the approximate realisation of continuous mappings by neural networks - Funahashi - 1989 |
| 1 | Approximation of dynamical systems by continuous-time recurrent approximate identity neural networks - Conti, Turchetti - 1994 |
| 1 | A class of Neural Networks based on Approximate Identity for Analog IC’s Hardware Implementation - Conti, Orcioni, et al. - 1994 |
| 1 | Fourier Theorems,” Cambridge Univ - Champeney - 1987 |
