A new neural structure with parallel and serial output via functional CPBUM neural network

Author

Lee, Tsu Tain ; Chen, Te Mu ; Jeng, Jin Tsong

Author_Institution

Dept. of Electr. Eng., Nat. Taiwan Univ. of Sci. & Technol., Taipei, Taiwan

Volume

4

fYear

2000

fDate

2000

Firstpage

2631

Abstract

The authors propose a new neural structure with parallel and serial output via functional CPBUM neural network. Specifically, we combine the advantages in series to series and parallel to parallel to develop a parallel and serial output learning structure. Hence, the proposed model can reduce the computational complexity via the similarity analysis and sensitivity analysis. It is shown that the similarity analysis can be employed to determine the knowledge base of the controller. Furthermore, it is also shown that the sensitivity analysis can provide valuable information between input-output training pairs

Keywords

Chebyshev approximation; computational complexity; feedforward neural nets; knowledge based systems; learning (artificial intelligence); neural net architecture; parallel processing; sensitivity analysis; Chebyshev Polynomials Based Unified Model neural net; computational complexity; functional CPBUM neural network; input-output training pairs; knowledge base; neural structure; parallel output; sensitivity analysis; serial output; serial output learning structure; similarity analysis; Artificial neural networks; Chebyshev approximation; Computational complexity; Electronic mail; Feedforward neural networks; Function approximation; Neural networks; Polynomials; Recurrent neural networks; Sensitivity analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 2000 IEEE International Conference on

Conference_Location

Nashville, TN

ISSN

1062-922X

Print_ISBN

0-7803-6583-6

Type

conf

DOI

10.1109/ICSMC.2000.884391

Filename

884391