A genetic algorithm based variable structure Neural Network

被引：4

作者：

Ling, SH ^{[1
]}

Lam, HK ^{[1
]}

Leung, FHF ^{[1
]}

Lee, YS ^{[1
]}

机构：

[1] Hong Kong Polytech Univ, Dept Elect & Informat Engn, Ctr Multimedia Signal Proc, Kowloon, Hong Kong, Peoples R China

来源：

IECON'03: THE 29TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1 - 3, PROCEEDINGS | 2003年

关键词：

genetic algorithm; neural network; hand-written pattern recognition;

D O I：

10.1109/IECON.2003.1280020

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship ((NR)-R-4) and a Network Switch Controller (NSC). In the (NR)-R-4, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the (NR)-R-4. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.

引用

页码：436 / 441

页数：6

共 12 条

[1] [Anonymous], NEURAL FUZZY ADAPTIV
[2] Holland J., 1992, ADAPTATION NATURAL A
[3] Fuzzy dynamic path planning using genetic algorithms
Juidette, H
Youlal, H
[J]. ELECTRONICS LETTERS, 2000, 36 (04) : 374 - 376
[4] LAM HK, IN PRESS IEEE T SY B
[5] Tuning of the structure and parameters of a neural network using an improved genetic algorithm
Leung, FHF
Lam, HK
Ling, SH
Tam, PKS
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (01): : 79 - 88
[6] LEUNG FHF, IN PRESS IEEE T IND
[7] LEUNG KF, IN PRESS IEEE T IND
[8] Ling SH, 2002, IEEE C EVOL COMPUTAT, P1928, DOI 10.1109/CEC.2002.1004538
[9] LING SH, IN PRESS IEEE T IND
[10] Michalewicz Z, 1994, Genetic Algorithms + Data Structures = Evolution Programs

← 1 2 →