Share Email Print
cover

Proceedings Paper

Constructing near-tight wavelet frames by neural networks
Author(s): Xin Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Suppose that (sigma) is a sigmoidal function which is the activation function of a neural network. Under certain assumptions on the derivatives of (sigma) , we show that a simple linear combination of dilates and translates of (sigma) generates a near tight wavelet frame for L2(R), which is then used in constructing approximation to multivariate functions by neural networks with one hidden layer.

Paper Details

Date Published: 23 October 1996
PDF: 11 pages
Proc. SPIE 2825, Wavelet Applications in Signal and Image Processing IV, (23 October 1996); doi: 10.1117/12.255226
Show Author Affiliations
Xin Li, Univ. of Nevada/Las Vegas (United States)


Published in SPIE Proceedings Vol. 2825:
Wavelet Applications in Signal and Image Processing IV
Michael A. Unser; Akram Aldroubi; Andrew F. Laine, Editor(s)

© SPIE. Terms of Use
Back to Top