Realization of RBF Neural Network with Local and Semi-Local Transfer Function Approximation and Classification

Mao Luo; Shao Yun Song

doi:10.4028/www.scientific.net/AMM.687-691.1628

Paper Titles

Pointwise Saturation Theorem of Bi-Continuous Semigroups
p.1612

The Growth of a Cosine Function Characterized by its Cogenerator
p.1616

The Application of MATLAB Simulation Technology on Evolutionary Game Analysis
p.1619

Scheme Automatic Generation Based on Full Life Cycle Assessment Gene Model of Structure
p.1622

Realization of RBF Neural Network with Local and Semi-Local Transfer Function Approximation and Classification
p.1628

The RBF Neural Network Learning Algorithm Based on Entropy Clustering and Competitive
p.1633

A Web Service Composition Algorithm Based on Graph Search and Semantic Web
p.1637

An Application of AHP and FAHP on the Model Prediction
p.1641

Resource Scheduling Optimization Model in Cloud Computing Environment
p.1645

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 687-691Realization of RBF Neural Network with Local and...

Realization of RBF Neural Network with Local and Semi-Local Transfer Function Approximation and Classification

Abstract:

Incremental Neural Network (IncNet) structure is controlled by the growth and pruning, and the complexity of the match and training data. Dual radial transfer function is more flexible than other commonly transfer function used in artificial neural network. Recent improvements in the multi-dimensional space (having the N-1 parameters) to increase the rotation of the transfer function of the constant value. Based on the results of the benchmark approach and psychological classification analysis clearly shows than any other classification network model has a stronger generalization.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 687-691)

Pages:

1628-1632

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.687-691.1628

Citation:

Cite this paper

Online since:

November 2014

Authors:

Mao Luo*, Shao Yun Song

Keywords:

Approximation, Artificial Neural Network (ANN), Classification, RBF, Transfer Function

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] R. Adamczak, W. Duch, and N. Jankowski. New developments in the Feature Space Mapping model. In Third Conference on Neural Networks and Their Applications, pages 65–70, Kule, Poland, Oct. (1997).

Google Scholar

[2] W. Duch and N. Jankowski. Survey of neural transfer functions. Neural Computing Surveys, 7, 1999. (submitted).

Google Scholar

[3] F. Girosi. An equivalence between sparse approximation and support vector machines. Neural Computation, 10(6), Aug. (1998).

DOI: 10.1162/089976698300017269

Google Scholar

[4] N. Jankowski. Ontogenic neural networks and their applications to classification of medical data. PhD thesis, Department of Computer Methods, Nicholas Copernicus University, Torun, Poland, 1999. (in preparation).

Google Scholar