Evolutionary artificial neural network based on Chemical Reaction Optimization

James J.Q. Yu; Albert Y.S. Lam; Victor O.K. Li

doi:10.1109/CEC.2011.5949872

Evolutionary artificial neural network based on Chemical Reaction Optimization

James J.Q. Yu^*
, Albert Y.S. Lam
, Victor O.K. Li

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

92 Scopus citations

Abstract

Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.

Original language	English
Title of host publication	2011 IEEE Congress of Evolutionary Computation, CEC 2011
Pages	2083-2090
Number of pages	8
DOIs	https://doi.org/10.1109/CEC.2011.5949872
State	Published - 2011
Externally published	Yes
Event	2011 IEEE Congress of Evolutionary Computation, CEC 2011 - New Orleans, LA, United States Duration: 5 Jun 2011 → 8 Jun 2011

Publication series

Name	2011 IEEE Congress of Evolutionary Computation, CEC 2011

Conference

Conference	2011 IEEE Congress of Evolutionary Computation, CEC 2011
Country/Territory	United States
City	New Orleans, LA
Period	5/06/11 → 8/06/11

Keywords

Artificial neural networks
chemical reaction optimization
evolutionary algorithm

Access to Document

10.1109/CEC.2011.5949872

Cite this

@inproceedings{6f678c54b6464c7a833411fb57ac8c3a,

title = "Evolutionary artificial neural network based on Chemical Reaction Optimization",

abstract = "Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.",

keywords = "Artificial neural networks, chemical reaction optimization, evolutionary algorithm",

author = "Yu, \{James J.Q.\} and Lam, \{Albert Y.S.\} and Li, \{Victor O.K.\}",

year = "2011",

doi = "10.1109/CEC.2011.5949872",

language = "英语",

isbn = "9781424478347",

series = "2011 IEEE Congress of Evolutionary Computation, CEC 2011",

pages = "2083--2090",

booktitle = "2011 IEEE Congress of Evolutionary Computation, CEC 2011",

note = "2011 IEEE Congress of Evolutionary Computation, CEC 2011 ; Conference date: 05-06-2011 Through 08-06-2011",

}

Yu, JJQ, Lam, AYS & Li, VOK 2011, Evolutionary artificial neural network based on Chemical Reaction Optimization. in 2011 IEEE Congress of Evolutionary Computation, CEC 2011., 5949872, 2011 IEEE Congress of Evolutionary Computation, CEC 2011, pp. 2083-2090, 2011 IEEE Congress of Evolutionary Computation, CEC 2011, New Orleans, LA, United States, 5/06/11. https://doi.org/10.1109/CEC.2011.5949872

Evolutionary artificial neural network based on Chemical Reaction Optimization. / Yu, James J.Q.; Lam, Albert Y.S.; Li, Victor O.K.
2011 IEEE Congress of Evolutionary Computation, CEC 2011. 2011. p. 2083-2090 5949872 (2011 IEEE Congress of Evolutionary Computation, CEC 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Evolutionary artificial neural network based on Chemical Reaction Optimization

AU - Yu, James J.Q.

AU - Lam, Albert Y.S.

AU - Li, Victor O.K.

PY - 2011

Y1 - 2011

N2 - Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.

AB - Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.

KW - Artificial neural networks

KW - chemical reaction optimization

KW - evolutionary algorithm

UR - https://www.scopus.com/pages/publications/80052008772

U2 - 10.1109/CEC.2011.5949872

DO - 10.1109/CEC.2011.5949872

M3 - 会议稿件

AN - SCOPUS:80052008772

SN - 9781424478347

T3 - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

SP - 2083

EP - 2090

BT - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

T2 - 2011 IEEE Congress of Evolutionary Computation, CEC 2011

Y2 - 5 June 2011 through 8 June 2011

ER -

Evolutionary artificial neural network based on Chemical Reaction Optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this