Book ChapterDOI
Wavelets based neural network for function approximation
Yong Fang,Tommy W. S. Chow +1 more
- pp 80-85
TLDR
The obtained results indicate that this new type of WNN exhibits excellent learning ability compared to the conventional ones, and the approximate error is significantly decreased.Abstract:
In this paper, a new type of WNN is proposed to enhance the function approximation capability. In the proposed WNN, the nonlinear activation function is a linear combination of wavelets, that can be updated during the networks training process. As a result the approximate error is significantly decreased. The BP algorithm and the QR decomposition based training method for the proposed WNN is derived. The obtained results indicate that this new type of WNN exhibits excellent learning ability compared to the conventional ones.read more
Citations
More filters
Journal ArticleDOI
Wavelet neural networks: A practical guide
TL;DR: This study presents a complete statistical model identification framework in order to apply WNs in various applications and shows that the proposed algorithms produce stable and robust results indicating that the framework can be applied inVarious applications.
Book ChapterDOI
Wavelet Neural Networks
TL;DR: A general accepted framework for applying WNs is missing from the literature as mentioned in this paper, which is a limitation of WNs in many applications, such as wireless sensor networks and wireless networks.
Journal ArticleDOI
Comparison of WAVENET and ANN for predicting the porosity obtained from well log data
TL;DR: An alternative method of porosity prediction, which is based on integration between wavelet theory and Artificial Neural Network (ANN) or wavelet network (wavenet), is presented and exhibits excellent learning ability compared to the conventional neural network with sigmoid or other activation functions.
Journal ArticleDOI
A comparative analysis of artificial neural network (ANN), wavelet neural network (WNN), and support vector machine (SVM) data-driven models to mineral potential mapping for copper mineralizations in the Shahr-e-Babak region, Kerman, Iran
TL;DR: An alternative method of mineral potential mapping is presented which is based on integration between wavelet theory and ANN or WNN, indicating that WNN method with POLYWOG 3 transfer function have high complex ability to learn and track unknown/undefined complex systems.
Journal ArticleDOI
Short-term Electric Load Forecasting Based on Wavelet Neural Network, Particle Swarm Optimization and Ensemble Empirical Mode Decomposition
TL;DR: A novel hybrid method for STLF based on ensemble empirical mode decomposition, wavelet neural network, and particle swarm optimization is proposed, which presents a new threshold approach based on the Brownian distance covariance to select the real IMFs.
References
More filters
Book
Ten lectures on wavelets
TL;DR: This paper presents a meta-analyses of the wavelet transforms of Coxeter’s inequality and its applications to multiresolutional analysis and orthonormal bases.
Journal ArticleDOI
The wavelet transform, time-frequency localization and signal analysis
TL;DR: Two different procedures for effecting a frequency analysis of a time-dependent signal locally in time are studied and the notion of time-frequency localization is made precise, within this framework, by two localization theorems.
Journal ArticleDOI
Wavelet networks
Qinghua Zhang,Albert Benveniste +1 more
TL;DR: A wavelet network concept, which is based on wavelet transform theory, is proposed as an alternative to feedforward neural networks for approximating arbitrary nonlinear functions.
Journal ArticleDOI
Wavelet neural networks for function learning
TL;DR: A wavelet-based neural network is described that has universal and L/sup 2/ approximation properties and is a consistent function estimator and performed well and compared favorably to the MLP and RBF networks.
Journal ArticleDOI
Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations
TL;DR: 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.