Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
CPBUM neural networks for modeling with outliers and noise
Applied Soft Computing
Expert Systems with Applications: An International Journal
Adaptive fuzzy wavelet network control design for nonlinear systems
Fuzzy Sets and Systems
An expert system for speaker identification using adaptive wavelet sure entropy
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Neurocomputing
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Wavelet neural networks: A practical guide
Neural Networks
Wavelet fuzzy LVQ based speaker verification system
International Journal of Speech Technology
Hi-index | 0.02 |
A representation of a class of feedforward neural networks in terms of discrete affine wavelet transforms is developed. It is shown that by appropriate grouping of terms, feedforward neural networks with sigmoidal activation functions can be viewed as architectures which implement affine wavelet decompositions of mappings. It is shown that the wavelet transform formalism provides a mathematical framework within which it is possible to perform both analysis and synthesis of feedforward networks. For the purpose of analysis, the wavelet formulation characterizes a class of mappings which can be implemented by feedforward networks as well as reveals an exact implementation of a given mapping in this class. Spatio-spectral localization properties of wavelets can be exploited in synthesizing a feedforward network to perform a given approximation task. Two synthesis procedures based on spatio-spectral localization that reduce the training problem to one of convex optimization are outlined