##plugins.themes.academic_pro.article.main##
Abstract
This paper presents the implementation of a Hebbian learning rule and genetic algorithm to store and later, recall of superimposed images of numerals in Hopfield network associative memory. A set of ten objects (i.e. 0 to 9 numerals) has been considered as the pattern set. In the Hopfield network associative memory, the weighted code of input patterns provides an auto-associative function in the network. The storing of images is done by hebbian learning rule and recalling is done by using both hebbian rule and genetic algorithm. The simulated results shows that the genetic algorithm gives efficient results as compared to hebbian rule for superimposed images of numerals.Â
Keywords- Hopfield Neural network, associative memory, hebbian learning rule, genetic algorithm, weight matrices, pattern recalling, population generation technique.##plugins.themes.academic_pro.article.details##
How to Cite
Meenakshi, R. P. A. K. (2015). Performance Analysis of Hopfield Network Associative Memory using Evolutionary Algorithm for Superimposed Images of Numerals. International Journal of Emerging Trends in Science and Technology, 2(07). Retrieved from http://igmpublication.org/ijetst.in/index.php/ijetst/article/view/824
References
1. Tanaka-Ynamawaki,M., (1992) “Human Generated Random Numbers and a Model of the Human Brain Functionsâ€, Department of Computer Science and Systems Engineering Faculty of Engineering, Miyazaki University, Miyazaki Japan, pp 889-2192.
2. Jesan,J.P. and Lauro,M.D., (2003) â€Human Brain and Neural Network Behaviourâ€. ACM publication.
3. Findley,D.M., (2009) “Thinking Like Human: A study of Human Brain and artificial Neural Network.†Westmoore High School 12613 S. Western Ave.Oklahoma City, pp. 73170.
4. Mangal, M. & Singh, M. P., (2007) “Analysis of Multidimensional XOR Classification Problem with Evolutionary Feed-forward Neural Networksâ€, International Journal on Artificial Intellig-ence Tools, Vol. 16, No.1, pp.111-120.
5. Yao, X., (1999) “Evolving artificial neural networksâ€, Proceeding of the IEEE, vol.87, no. 9,pp.1423-1447.
6. Pal,S.K., De,S. & Ghosh, A., (1997) “Designing Hopfield type networks using genetic algorithms and its comparison with simulated annealingâ€, Intl Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 3 pp-447-461.
7. Salcedo-Sanz,S. & Yao,X., (2004) “A Hybrid Hopfield Network-Genetic Algorithm Approach for the Terminal Assignment Problem†IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, Vol. 34, No. 6, pp. 2343-2353.
8. Jiyou Xu,J.H., & Yao,X., (2000) “Solving Equations by Hybrid Evolutionary Computation Techniquesâ€, IEEE Transactions on Evolutionary Computation, Vol. 4, Issue 3, pp. 295-304.
9. Mangal, M. & Singh, M. P., (2006) “Handwritten English Vowels using Hybrid Evolutionary Feed-forward Neural Networkâ€, Malaysian Journal of Computer Science, Vol. 19, No. 2, pp. 169-187.
10. Imada, A., Araki K.., “Evolved Asymmetry and Dilution of Random Synaptic Weights in HopfieldNetwork Turn a Spin-glass Phase into Associative Memoryâ€, The 2nd International Conference on Computational Intelligence and Neuroscience proceedings of Joint Conference of Computer Science, Vol. 2 (1997) 223-226.
11. Imada, A., Araki K.,†Hopfield Model of Associative Memory as a Test Function of Evolutionary Computationsâ€, The 1st International Workshop on Frontiers in Evolutionary Algorithms,Proceedings of Joint Conference of Computer Science, Vol. 1 (1997) 180-183.
12. Shrivastava, S., Singh, M.P., “Performance evaluation of feed-forward neural network with soft computing techniques for hand written English alphabets, Applied soft Computing Journal, Vol. 11(1) (2011) 1156-1182.
13. Kumar, S., Singh, M.P., “Pattern recalling analysis of English alphabets using Hopfield model of feedback neural network with evolutionary searchingâ€, International Journal of Business Information Systems, Vol. 6(2) (2010) 200-218.
14. Singh, T.P., Jabin, S., Singh, M. “Evolving Weight Matrices to increase the Capacity of Hopfield Neural Network Associative Memory using Hybrid Evolutionary Algorithmâ€, Proceedings of 2010 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC 2010), art. no. 5705809, pp. 434-438, doi 10.1109/ICCIC.2010.5705809.
2. Jesan,J.P. and Lauro,M.D., (2003) â€Human Brain and Neural Network Behaviourâ€. ACM publication.
3. Findley,D.M., (2009) “Thinking Like Human: A study of Human Brain and artificial Neural Network.†Westmoore High School 12613 S. Western Ave.Oklahoma City, pp. 73170.
4. Mangal, M. & Singh, M. P., (2007) “Analysis of Multidimensional XOR Classification Problem with Evolutionary Feed-forward Neural Networksâ€, International Journal on Artificial Intellig-ence Tools, Vol. 16, No.1, pp.111-120.
5. Yao, X., (1999) “Evolving artificial neural networksâ€, Proceeding of the IEEE, vol.87, no. 9,pp.1423-1447.
6. Pal,S.K., De,S. & Ghosh, A., (1997) “Designing Hopfield type networks using genetic algorithms and its comparison with simulated annealingâ€, Intl Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 3 pp-447-461.
7. Salcedo-Sanz,S. & Yao,X., (2004) “A Hybrid Hopfield Network-Genetic Algorithm Approach for the Terminal Assignment Problem†IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, Vol. 34, No. 6, pp. 2343-2353.
8. Jiyou Xu,J.H., & Yao,X., (2000) “Solving Equations by Hybrid Evolutionary Computation Techniquesâ€, IEEE Transactions on Evolutionary Computation, Vol. 4, Issue 3, pp. 295-304.
9. Mangal, M. & Singh, M. P., (2006) “Handwritten English Vowels using Hybrid Evolutionary Feed-forward Neural Networkâ€, Malaysian Journal of Computer Science, Vol. 19, No. 2, pp. 169-187.
10. Imada, A., Araki K.., “Evolved Asymmetry and Dilution of Random Synaptic Weights in HopfieldNetwork Turn a Spin-glass Phase into Associative Memoryâ€, The 2nd International Conference on Computational Intelligence and Neuroscience proceedings of Joint Conference of Computer Science, Vol. 2 (1997) 223-226.
11. Imada, A., Araki K.,†Hopfield Model of Associative Memory as a Test Function of Evolutionary Computationsâ€, The 1st International Workshop on Frontiers in Evolutionary Algorithms,Proceedings of Joint Conference of Computer Science, Vol. 1 (1997) 180-183.
12. Shrivastava, S., Singh, M.P., “Performance evaluation of feed-forward neural network with soft computing techniques for hand written English alphabets, Applied soft Computing Journal, Vol. 11(1) (2011) 1156-1182.
13. Kumar, S., Singh, M.P., “Pattern recalling analysis of English alphabets using Hopfield model of feedback neural network with evolutionary searchingâ€, International Journal of Business Information Systems, Vol. 6(2) (2010) 200-218.
14. Singh, T.P., Jabin, S., Singh, M. “Evolving Weight Matrices to increase the Capacity of Hopfield Neural Network Associative Memory using Hybrid Evolutionary Algorithmâ€, Proceedings of 2010 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC 2010), art. no. 5705809, pp. 434-438, doi 10.1109/ICCIC.2010.5705809.