GG WALTER’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (1)


WAVELET NEURAL NETWORKS FOR FUNCTION LEARNING
  • Article

June 1995

·

78 Reads

·

144 Citations

IEEE Transactions on Signal Processing

J ZHANG

·

GG WALTER

·

YB MIAO

·

WNW LEE

In this paper, a wavelet-based neural network is described. The structure of this network is similar to that of the radial basis function (RBP) network, except that here the radial basis functions are replaced by orthonormal scaling functions that are not necessarily radial symmetric. The efficacy of this type of network in function learning and estimation is demonstrated through theoretical analysis and experimental results. In particular, it has been shown that the wavelet network has universal and L(2) approximation properties and is a consistent function estimator. Convergence rates associated with these properties are obtained for certain function classes where the rates avoid the ''curse of dimensionality.'' In the experiments, the wavelet network performed well and compared favorably to the MLP and RBF networks.

Citations (1)


... There are many different neural network architectures for which the UAP has been shown to hold in various topological spaces (cf. Cybenko [13], Funahashi [18], Hornik [26], Hornik et al. [27], Kidger and Lyons [32], Leshno et al. [36], Liao et al. [38], Mhaskar and Micchelli [43], Park and Sandberg [45,46], Pinkus [47] and Zhang et al. [55]). For ease of presentation, we discuss the class of feedforward neural networks, also called multilayer perceptrons or multilayer feedforward neural networks. ...

Reference:

Importance sampling for option pricing with feedforward neural networks
WAVELET NEURAL NETWORKS FOR FUNCTION LEARNING
  • Citing Article
  • June 1995

IEEE Transactions on Signal Processing