On the approximation of stochastic processes by approximate identity neural networks

  title={On the approximation of stochastic processes by approximate identity neural networks},
  author={Claudio Turchetti and Massimo Conti and Paolo Crippa and Simone Orcioni},
  journal={IEEE transactions on neural networks},
  volume={9 6},
The ability of a neural network to learn from experience can be viewed as closely related to its approximating properties. By assuming that environment is essentially stochastic it follows that neural networks should be able to approximate stochastic processes. The aim of this paper is to show that some classes of artificial neural networks exist such that they are capable of providing the approximation, in the mean square sense, of prescribed stochastic processes with arbitrary accuracy. The… CONTINUE READING
Highly Cited
This paper has 51 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 14 references

A CMOS analog neuro-chip with stochastic learning and multilevel weight storage

inIEEE Proc. Int. Symp. Circuits Syst.’97 ISCAS97,Hong Kong, June 9–12, 1997, pp. 1844–1847. • 1997
View 3 Excerpts

A class of neural networks based on approximate identity for analog IC’s hardware implementation

M. Conti, S. Orcioni, C. Turchetti
IEICE Trans. Fundamentals, vol. E77-A, no. 6, pp. 1069–1079, June 1994. • 1994
View 2 Excerpts

Approximate identity neural networks for analog synthesis of nonlinear dynamical systems

C. Turchetti, M. Conti
IEEE Trans. Circuits Syst. I,vol. 41, pp. 841–858, Dec. 1994. • 1994

Universal approximation using radialbasisfunction networks

I. W. Sandberg
Neural Comput • 1991

Networks for approximation and learning,

T. Poggio, F. Girosi
Proc. IEEE,vol • 1990
View 3 Excerpts

Similar Papers

Loading similar papers…