CFP last date
20 December 2024
Reseach Article

Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network

by G. V. R. Sagar, S. Venkata Chalam
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 53 - Number 4
Year of Publication: 2012
Authors: G. V. R. Sagar, S. Venkata Chalam
10.5120/8410-2047

G. V. R. Sagar, S. Venkata Chalam . Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network. International Journal of Computer Applications. 53, 4 ( September 2012), 23-28. DOI=10.5120/8410-2047

@article{ 10.5120/8410-2047,
author = { G. V. R. Sagar, S. Venkata Chalam },
title = { Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network },
journal = { International Journal of Computer Applications },
issue_date = { September 2012 },
volume = { 53 },
number = { 4 },
month = { September },
year = { 2012 },
issn = { 0975-8887 },
pages = { 23-28 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume53/number4/8410-2047/ },
doi = { 10.5120/8410-2047 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:53:16.809431+05:30
%A G. V. R. Sagar
%A S. Venkata Chalam
%T Simultaneous Evolution of Architecture and Connection Weights in Artificial Neural Network
%J International Journal of Computer Applications
%@ 0975-8887
%V 53
%N 4
%P 23-28
%D 2012
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The important issue for Designing architecture isthe evolution of Artificial Neural Network (ANN). There is no systematic method to design a near-optimal architecture for a given application or task. The pattern classification methods are used to design the neural network architectures and efforts towards the automatic design of network topologies, constructive and destructive algorithms can be used. In the proposed work the optimization of architectures and connection weights uses the evolutionary process. A single-point crossover is applied with selective schemas on the network space and evolution is introduced in the mutation stage so that an optimized ANNs are achieved.

References
  1. X. Yao. Evolvingartificialneuralnetworks. In ProceedingsonIEEE,pages1423–1447, 1999.
  2. X. YaoandY. Liu. Anewevolutionary systemforevolving artificialneuralnetworks. IEEETransactionson NeuralNetworks,8(3):694–713,May1997.
  3. M. C. MozeandP. Smolensky. Usingrelevancetoreduce networksizeautomatically. connectionScience,1(1):3–16, 1989.
  4. X. YaoandY. Liu. Towardsdesigningartificial networksby evolution. AppliedMathematicsandComputation,91(1):83–90,1998.
  5. G. F. Miller,P. M. Todd,andS. U. Hegde. Designingneural networksusinggeneticalgorithms. InJ. D. Schaffer,editor, ProceedingsoftheThirdInternationalConferenceonGeneticAlgorithms,pages379–384,1989.
  6. D. Whitley, T. Starkweather,andC. Bogart. Geneticalgorithmsandneuralnetworks:Optimizing connectionsandconnectivity. Parallelcomputing,14:347–361,1993.
  7. P. J. B. Hancock. Geneticalgorithms andpermutationproblems: Acomparisonof recombination operatorsforneuralnetstructurespecification. InL. D. Whitleyand J. D. Schaffer,editors,ProceedingsoftheThirdInternationalWorkshoponCombinationsGeneticAlgorithmsNeuralNetworks,pages108–122,1992GeneticAlgorithms,pages379–384,1989.
  8. X. Yao and Y. Liu, "EPNet for chaotic time-series prediction,"in Select. Papers 1st Asia-Pacific Conf. Simulated Evolution andLearning (SEAL'96), vol. 1285 of Lecture Notes in ArtificialIntelligence, X. Yao, J. H. Kim, and T. Furuhashi, Eds. Berlin, Germany: Springer-Verlag, 1997, pp. 146–156.
  9. Y. Liu and X. Yao, "A population-based learning algorithmwhich learns both architectures and weights of neural networks," Chinese J. Advanced Software Res. , vol. 3, no. 1, pp. 54–65, 1996.
  10. D. B. Fogel, "Phenotypes, genotypes, and operators in Evolutionarycomputation," in Proc. 1995 IEEE Int. Conf. EvolutionaryComputation (ICEC'95), Perth, Australia, pp. 193–198.
  11. D. G. Stork, S. Walker, M. Burns, and B. Jackson, "Preadaptationin neural circuits," in Proc. Int. Joint Conf. Neural Networks, vol. I, Washington, DC, 1990, pp. 202–205.
  12. D. White and P. Ligomenides, "GANNet: A genetic Algorithmfor optimizing topology and weights in neural network design, "in Proc. Int. Workshop Artificial Neural Networks (IWANN'93),Lecture Notes in Computer Science, vol. 686. Berlin,Germany: Springer-Verlag, 1993, pp. 322–327.
  13. K. Stanley andR. Miikkulainen. Evolvingneuralnetworksthroughaugmenting topologies. EvolutionaryComputation,10(2):99–127,2002.
  14. K. O. StanleyandR. Miikkulainen. Efficientevolutionofneuralnetworktopologies. InProceedingsoftheCongressonEvolutionaryComputation,CEC'02,pages1757–1762. IEEEComputerSocietyPress,2002.
  15. Daniel Rivero, Julian Dorado, Juan R, and Rabunal, "Artificial neural Network Development by means of genetic programming with graph codification", Proceedings of world academy of science, engineering and technology, Vol:15, pp 209-214, 2006.
  16. Dario Floreano Æ Peter Du¨rr Æ Claudio Mattiussi , " Neuro-evolution: from architectures to learning," Springer-Verlag, January 2008.
  17. G. V. R. Sagar, et al. "Evolutionary Algorithm for Optimal Connection weights in Artificial Neural Networks," IJE, vol. 5, Issue: 5, 2011.
  18. G. V. R. Sagar, S. V. Chalam "Evolutionary ANN Learning algorithm on Benchmark andReal time dataset Classification problems," Current Development in Artificial Intelligence (CDAI), Aug 2012
Index Terms

Computer Science
Information Sciences

Keywords

Artificial neural network topology mutation schema theory