<title>Constructing near-tight wavelet frames by neural networks</title>

Xin LiProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 1996 · DOI

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 L<SUP>2</SUP>(R), which is then used in constructing approximation to multivariate functions by neural networks with one hidden layer.
BibTeX
@inproceedings{li1996lt,
  author = {Xin Li},
  title = {{\&lt;title\&gt;Constructing near-tight wavelet frames by neural networks\&lt;/title\&gt;}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {1996},
  doi = {10.1117/12.255226},
}

Loading related content...

Figure