Direction-basis-function neural networks

Author

Shoujue, Wang ; Jingpu, Shi ; Chuan, Chen ; Yujian, Li

Author_Institution

Inst. of Semicond., Acad. Sinica, Beijing, China

Volume

2

fYear

1999

fDate

36342

Firstpage

1251

Abstract

A model called direction-basis-function (DBF) neural networks and its relevant algorithm for pattern classification are proposed. Also, one implementation of the model based on the architecture of priority ordered neural networks (PONN), that is PODBFN, is discussed. When adapted as pattern classifier, the neurons with linear output are used in the course of learning, while hard limited step activation function is for pattern classification. The computer simulations show that not only the convergence speed is much faster than the improved BP algorithm, but also the performance of the network is better. The DBF pattern classifier was implemented on the micro-neural computer CASSANDRA-I, and the experimental results obtained are presented

Keywords

convergence; learning (artificial intelligence); neural nets; pattern classification; activation function; convergence; direction-basis-function neural networks; learning; pattern classification; priority ordered neural networks; Classification algorithms; Computer architecture; Computer simulation; Convergence; Feedforward neural networks; Neural networks; Neurons; Optimization methods; Pattern classification; Radial basis function networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.831140

Filename

831140