CFP last date
20 January 2025
Reseach Article

Comparative Analysis of Recurrent Networks for Pattern Storage and Recalling of Static Images

by Jay Kant Pratap Singh Yadav, Laxman Singh, Zainul Abdin Jaffery
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 170 - Number 10
Year of Publication: 2017
Authors: Jay Kant Pratap Singh Yadav, Laxman Singh, Zainul Abdin Jaffery
10.5120/ijca2017914918

Jay Kant Pratap Singh Yadav, Laxman Singh, Zainul Abdin Jaffery . Comparative Analysis of Recurrent Networks for Pattern Storage and Recalling of Static Images. International Journal of Computer Applications. 170, 10 ( Jul 2017), 15-19. DOI=10.5120/ijca2017914918

@article{ 10.5120/ijca2017914918,
author = { Jay Kant Pratap Singh Yadav, Laxman Singh, Zainul Abdin Jaffery },
title = { Comparative Analysis of Recurrent Networks for Pattern Storage and Recalling of Static Images },
journal = { International Journal of Computer Applications },
issue_date = { Jul 2017 },
volume = { 170 },
number = { 10 },
month = { Jul },
year = { 2017 },
issn = { 0975-8887 },
pages = { 15-19 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume170/number10/28106-2017914918/ },
doi = { 10.5120/ijca2017914918 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:18:06.852959+05:30
%A Jay Kant Pratap Singh Yadav
%A Laxman Singh
%A Zainul Abdin Jaffery
%T Comparative Analysis of Recurrent Networks for Pattern Storage and Recalling of Static Images
%J International Journal of Computer Applications
%@ 0975-8887
%V 170
%N 10
%P 15-19
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Auto associative memory is widely used network for pattern storage and recalling of patterns. Hopfield network, Hamming network are popularly known auto associative memory networks. In this paper we present comparative analysis in term of storage and recalling efficiency of Hopfield network and Hamming network and we choose images of letters. The results of the simulation for Hopfield and hamming network for character recognition under high noise are delineated and mentioned.

References
  1. J.J. Hopfield, “Neural Networks and physical systems with emergent collective computational abilities,” Proc. Natl. Acad. Sci. USA, 1982, 79, 2554 — 2558.
  2. I. Kanter and H. Sompolinsky, “Associative Recall of memory without errors,” Phys. Rev. A, 1987, vol. 35, pp. 380-392.
  3. Y.P. Zaychenko, “Fundamentals of intellectual systems design,” Kiev. Publishing House, Slovo, 2004, pp. 352. (rus).
  4. B. Yegnanarayana, Artificial Neural Networks,” Prentice Hall of India, 2006.
  5. Neil Davey, S.P. Hunt and Rod Adams, “High Capacity Recurrent Associative Memories,” Neurocomputing – IJON, 2004, vol. 62, pp. 459-491, DOI: 10.1016/j.neucom.2004.01.007.
  6. F.L. Chung and T. Lee, “Fuzzy competitive learning,” Neural Netw. 7, 1994, 539 – 552.
  7. W. Tarkowski, M. Lewenstein and A. Nowak, “Optimal Architectures for Storage of Spatially Correlated Data in Neural Network Memories,” ACTA Physica Polonica B, 1997, vol. 28, No. 7, pp. 1695 - 1705.
  8. K. Deb and D. Anand Joshi, “A. Real-coded evolutionary algorithms with parent-centric recombination,” In: Proceedings of the IEEE Congress on Evolutionary Computation, 2002, pp. 61 – 66.
  9. J.J. Hopfield, “Neurons, dynamics and computation,” Phys. Today, 47, 40 – 46, 1994, 78 2 Neural Networks with Feedback and Self-organization.
  10. S. Heykin, “Neural networks,” Full course (2nd edn), Transl. engl., Moscow.-Publishing House Williams, 2006, pp.1104. (rus).
  11. Christophe L. Labiouse, Albert A. Salah and Irina Starikova, “The Impact of Connectivity on the Memory Capacity and the Retrieval Dynamics of Hopfield – type Networks,” Proc. Of the Santa Fc Complex Systems Summer School, pp. 77-84.
  12. Mikhail Z Zgurobsky and Yuriy P Zaychenko, “The Fundamental of Computational Intelligence,” Springer International Publishing Switzerland, 2016, pp.- 39-59.
  13. T. Kohonen, “Self-Organization and Associative Memory,” 3rd ed., Berlin Springer-Verlag, 1989.
  14. T. Kohonen and M. Ruohonen, “Representation of Associated Data by Matrix Operators,” IEEE Trans. Computers C – 22(7), pp. 701-702.
  15. N. Davey, S. Hunt and R. Adams, “High Capacity Recurrent Associative Memories,” 2004, Neurocomputing – IJON 62, 459 - 491.
Index Terms

Computer Science
Information Sciences

Keywords

Auto associative Pattern Recurrent network Hebbian rule