Abstract

In this paper we are studying the tolerance of Hopfield neural network for storage and recalling of fingerprint images. The feature extraction of these images is performed with FFT, DWT and SOM. These feature vectors are stored as associative memory in Hopfield Neural Network with Hebbian learning and Pseudoinverse learning rules. The objective of this study is to determine the optimal weight matrix for efficient recalling of the memorized pattern for the presented noisy or distorted and incomplete prototype patterns from the Hopfield network. This study also explores the tolerance in Hopfield neural network for reducing the effect of false minimas in the recalling process. Besides this the capabilities of learning rules for pattern storage is also analyzed. This study also exhibits the analysis as pattern storage networks for feature vectors obtained from SOM with FFT and DWT

References

• B. Yegnanarayana, Artificial Neural Networks, Prentice Hall of India, 2006.
• W. Tarkowski, M. Lewenstein, 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.
• Kevin Takasaki, "Critical Capacity of Hopfield Networks", MIT Department of Physics, 2007, URL: http://web. mit. edu. physics/.
• Gang Wei, Zheyuan Yu, "Storage Capacity of Letter Recognition in Hopfield Networks", Faculty of Computer Science, Dalhousie University, http://citeseer. ist. psu. edu/584397. html
• Neil Davey, S. P Hunt, Rod Adams, "High Capacity Recurrent Associative Memories", Neurocomputing - IJON, 2004, vol. 62, pp. 459 - 491, DOI: 10. 1016/j. neucom. 2004. 02. 007.
• Amos Storkey, "Increasing the Capacity of a Hopfield Network Without Sacrificing Functionality", Artificial Neural Networks – ICANN'97, 1997, 451 – 456.
• D. J. Amit, H. Gutfreund, H. Sompolinsky, "Storing infinite number of patterns in a spin Glass Model of Neural Networks. ", Physical Review Letters 55, pp 1530 - 1533.
• Frank Emmert Streib, "Active Learning in Recurrent Neural Networks Facilitated by a Hebb-like Learning Rule with Memory", Neural Information Processing – Letters and Reviews, November 2005, Vol. 9, No. 2, pp 31 – 40.
• Christophe L. Labiouse, Albert A. Salah, Irina Starikova, "The Impact of Connectivity on the Memory Capacity and the Retrieval Dynamics of Hopfield –type Networks", Proc. Of the Santa Fe Complex Systems Summer School, pp. 77-84
• Dmitry O. Gorodnichy, "The Influence of Self Connection on the Performance of Pseudoinverse Autoassociative Networks", Proceedings of CVPR Workshop on Face Processing in Vodeo(FPIV '04), 2004.
• T. Kohonen, M. Ruohonen, "Representation of Associated Data by Matrix Operators", IEEE Trans. Computers C-22(7), pp 701 - 702.
• I. Kanter, H. Sompolinsky, "Associative Recall of memory without errors", Phys. Rev. A (1987), vol 35, pp 380 - 392.
• Nicholas Sandirasegaram, Ryan English, "Comparative Analysis of Feature Extraction (2D FFT & Wavelet) and Classification (Lp metric distances, MLP NN & HNet) algorithms for SAR imagery", Procedings Of SPIE, 2005, Vol. 5808, pp 314 - 325.
• Zafer Iscan, Mehmet Nadir Kurnaz, Zumray Dokur, Tamer Plemz, "Ultrasound Image Segmentation by Using Wavelet Transform and Self Organizing Neural Network", Neural Information Processing - Letters and Reviews, 2006, Vol. 10, Nos. 8-9, pp. 183 - 191.
• D. K. Sharma, Loveleen Gaur, Daniel Okunbor, "Image Compression and Feature Extraction with Neural Network", Proceedings of Academy the of Information and Management Sciences, 2007, Volume 11, No. 1, pp 33 - 37
• Jiwen Lu, Yongwei Zhao, Yanxue Xue, Junlin Hu, "Palmprint Recognition via Locality Preserving Projections and Extreme Learning Machine Neural Network", Proceedings ICSP, 2008, pp 2096 - 2099.
• P. Tavan, H. Grubmeller, H. Kuhnel, "Self Organization of Associative Memory and Pattern Classification: Recurrent Signal Processing on Topological Feature Maps", Biological Cybernetics, Springer Verlag, 1990, 64, pp 95 - 105
• F. Alim Ferha, H. Bessalah, S. Seddiki, M. Issad, O. Kerdjidj, H. Salhi, "WT-SOM network implementation on FPGA for medical images compression", Proceedings of the 5th International Conference on Soft Computing as transdisciplinary science and technology (CSTST 2008), pp 464 - 468.
• Teuvo Kohonen, "Self Organising Map", Proceedings of the IEEE, September 1990, Vol. 78, No. 9, pp 1464 - 1480
• Sumeet Gill, Naveen Kumar Sharma, Manu Pratap Singh, "Study of Pattern Storage Techniques in Self Organizing Map using Hopfield Energy Function Analysis", Proceedings of ADCOM - 2006, pp 640 - 641, 1-4244-0716-8/06/2006/IEEE.
• Sylvain Chartier, Richard Lepage, "Learning and Extracting Edges from Images by a Modified Hopfield Neural Network", Proceedings of the 16th International Conference on Pattern Recognition, 2002, pp-30431.
• S. Y. Kung, "Digital Neural Networks", New Jersey: Prentice-Hall, 1993.
• M. W. Hirsch, Convergent activation dynamics in continuous time networks, Neural Networks, 1989, v. 2 n. 5, p. 331-349.
• M. V. Tsodyks, Feigel'man, "The enhanced storage capacity in neural networks with low activity levels",M. V. , Europhys. Lett. , 1988, vol. 6 (2), pp. 101–105.
• T. Kohonen, "Self-organized formation of topologically correct feature maps", Biol. Cybernet. , 1982b, vol. 43, pp. 59-69.
• S. kaski, J. kangas, T. kohonen, Bibliography of self-organizing map (SOM) papers: 1981-1997. Neural computing surveys, 1(3&4): 1-176, 1998.
• J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation. Addison-Wesley, 1991.
• D. H. Hubel and T. N. Wiesel, "Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex," J. Physiol. London, 1962, vol. 160, pp. 106-154.
• J. J. Hopfield,"Neurons with Graded Response Have Collective Computational Properties like those of Two-State Neurons," proceedings of national academy of sciences, vol. 81, 1984, pp. 3088-92. Reprinted in 1988, Anderson and Rosenfeld
• , pp. 460-4.
• Manu P. Singh, K. V. Arya, K. Sharma, " Video Compression using Self Organising Map and Pattern Storage using Hopfield Neural Network", Fourth International Conference on Industrial and Information Systems, ICIIS 2009, pp. 272 - 277.
• T. Kohonen, "Self-Organization and Associative Memory", 3rd ed. , Berlin Springer-Verlag, 1989.
• T. Kohonen, "Analysis of Simple Self-Organizing Process", Biological. Cybernetics, 1982a, vol. 44, pp. 135-140.
• Somesh Kumar, Manu P. Singh, "Study of Hopfield neural network with sub-optimal and random GA for pattern recalling of English characters", Elsevier, Applied Soft Computing, Volume 12, Issue 8, 2012, 2593 - 2600.
• Agnes Meyder, Constantin Kiderlen, "Fundamental Properties of Hopfield Networks and Boltzmann Machines for Associative Memories", Machine Learning, vt 2008.