The week's pick
Reseach Article
Enhancing the Delta Training Rule for a Single Layer Feedforward Heteroassociative Memory Neural Network
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 96 - Number 1 |
| Year of Publication: 2014 |
| Authors: Omar Waleed Abdulwahhab |
10.5120/16759-6314
|
Omar Waleed Abdulwahhab . Enhancing the Delta Training Rule for a Single Layer Feedforward Heteroassociative Memory Neural Network. International Journal of Computer Applications. 96, 1 ( June 2014), 23-27. DOI=10.5120/16759-6314
Abstract
In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1. 6% and 3. 2% special partially described noisy inputs patterns are presented.
References
- Zurada,J. M. 1992. Introduction to artificial neural systems, West publishing company.
- Sarangapani, J. 2006. Neural network control of nonlinear discrete –time systems, Taylor and Francis.
- Fausett, L. 1994. Fundamental of neural networks, Prentice Hall.
- Sudo,, A. , Sato, A. , and Hasegawa, O. 2009. Associative memory for online learning in noisy environments using self-organizing incremental neural network. IEEE transactions on neural networks, Vol. 20, No. 6, pp. 972, June 2009.
- Badri, L. 2010. Development of Neural Networks for Noise Reduction. The International Arab Journal of Information Technology, Vol. 7, No. 3, pp. 289-294, July 2010.
- Singh,, Y. P. , Yadav, V. S. , Gupta, A. and Khare, A. 2009. Bidirectional associative memory neural network method in the character recognition. Journal of Theoretical and Applied Information Technology, Vol 5, No. 4, 2009.
- Boutalis, Y. S. 2011. A new method for constructing kernel vectors in morphological associative memories of binary patterns. Computer Science and Information Systems, Vol. 142 8, No. 1, pp. 141-166, January 2011.
- Inohira,, Ogawa, E. T. and Yokoi, H. 2008. Associative Memory with Pattern Analysis and Synthesis by a Bottleneck Neural Network. Biomedical Soft Computing and Human Sciences, Vol. 13, No. 2, pp. 27-34, 2008.
- Rodríguez, D. , Casermeiro, E. , and Lobato, J. 2007. Hopfield Network as Associative Memory with Multiple Reference Points. World Academy of Science, Engineering and Technology, Issue 0007, pp. 622-627, July 2007.
- Yaakobi, E. and Bruck, J. 2012. On the Uncertainty of Information Retrieval in Associative Memories. IEEE International Symposium on Information Theory Proceedings, 2012.
- Sommer, F. T. and Dayan, P. 1998. Bayesian Retrieval in Associative Memories with Storage Errors. IEEE transactions on neural networks, Vol. 9, No. 4, July 1998.
- Zeng, X. and Martinez, T. 2003. A Noise Filtering Method Using Neural Networks. International Workshop on Soft Computing Techniques in Instrumentation, Measurement and Related Applications Provo. Utah, USA, 17 May 2003.
- Van Gorp, J. , Schoukens J. , and Pintelon, R. 1998. Adding Input Noise to Increase the Generalization of Neural Networks is a Bad Idea. Intelligent Engineering Systems Through Artificial Neural Networks, Volume 8. , pp. 127 – 132, 1998.
- Steege, F. , Stephan, V. , and Grob, H. 2012. Effects of Noise-Reduction on Neural Function Approximation. Proc. 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 73-78, 2012.
- Sussner , P. and Valle, M. 2006. Gray-scale Morphological Associative Memories. IEEE transactions on neural networks, vol. 17, no. 3, May 2006.
Index Terms
Keywords