Genetic algorithms and evolutionary programming hybrid strategy for structure and weight learning for multilayer feedforward neural networks

被引：17

作者：

Gao, FR ^{[1
]}

Li, MZ ^{[1
]}

Wang, FL ^{[1
]}

Wang, BG ^{[1
]}

Yue, PL ^{[1
]}

机构：

[1] Hong Kong Univ Sci & Technol, Dept Chem Engn, Kowloon, Peoples R China

来源：

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH | 1999年 / 38卷 / 11期

关键词：

D O I：

10.1021/ie990256h

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

A hybrid strategy (GAs-EP) combining genetic algorithms (GAs) and evolutionary programming (EP) via a matrix group encoding is proposed to evolve a multilayer feedforward neural network, through simultaneously acquiring the network structure and weights. The strategy uses EP for evolving neural network and GAs for diversifying the individuals of the neural network population. This strategy inherits the strengths and suppresses the shortcomings of GAs and EP in their separate forms. The resulting strategy is simple and practical, and it has fast convergence. Its effectiveness has been demonstrated through its application to the polymer melt temperature prediction of injection molding.

引用

页码：4330 / 4336

页数：7

共 10 条

[1] AN EVOLUTIONARY ALGORITHM THAT CONSTRUCTS RECURRENT NEURAL NETWORKS [J].

ANGELINE, PJ ;

SAUNDERS, GM ;

POLLACK, JB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (01) :54-65

[2] AN INTRODUCTION TO SIMULATED EVOLUTIONARY OPTIMIZATION [J].

FOGEL, DB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (01) :3-14

[3] A neural linearizing control scheme for nonlinear chemical processes [J].

Kim, SJ ;

Lee, MH ;

Park, SW ;

Lee, SY ;

Park, CH .

COMPUTERS & CHEMICAL ENGINEERING, 1997, 21 (02) :187-200

[4] MODIFIED HOPFIELD NEURAL NETWORKS FOR RETRIEVING THE OPTIMAL SOLUTION [J].

LEE, BW ;

SHEU, BJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (01) :137-142

[5] GENETIC EVOLUTION OF THE TOPOLOGY AND WEIGHT DISTRIBUTION OF NEURAL NETWORKS [J].

MANIEZZO, V .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (01) :39-53

[6]

Milanic S, 1997, COMPUT CHEM ENG, V21, pS637

[7] The dependence identification neural network construction algorithm [J].

Moody, JO ;

Antsaklis, PJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (01) :3-15

[8] PRUNING ALGORITHMS - A SURVEY [J].

REED, R .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (05) :740-747

[9] Back-propagation neural network adaptive control of a continuous wastewater treatment process [J].

Syu, MJ ;

Chen, BC .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 1998, 37 (09) :3625-3630

[10] Strategies for modeling and control of nonlinear chemical processes using neural networks [J].

Wang, H ;

Oh, Y ;

Yoon, ES .

COMPUTERS & CHEMICAL ENGINEERING, 1998, 22 :S823-S826

← 1 →