Abstract

This paper analyzes the Hopfield neural network for storage and recall of fingerprint images. The paper first discusses the storage and recall via hebbian learning rule and then the performance enhancement via the pseudo-inverse learning rule. Performance is measured with respect to storage capacity; recall of distorted or noisy patterns. Here we test the accretive behavior of the Hopfield neural network.

References

• Kevin Takasaki, “Critical Capacity of Hopfield Networks”, MIT Department of Physics, 2007.
• Ramasamy Ramachandran, Natarajan Gunusekharan, “Optimal Implementation of two Dimensional Bipolar Hopfield Model Neural Network”, Proc. Natl. Sci. Counc. ROC(A), 2000, Vol. 24(1), pp 73 – 78.
• 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
• J.Ma, “The Object Perceptron Learning Algorithm on Generalised Hopfield Networks for Associative Memory”, Neural Computing and Applications, 1999, Vol. 8, 25 – 32.
• N. Davey, S.P Hunt, “The Capacity and Attractor Basins of Associative Memory Models”.
• Sylvain Chartier, Richard Lepage, “Learning and Extracting Edges from Images by a Modified Hopfield Neural Network”, 2002.
• Mahmoud I. A. Abdulla, Hanaa Shaker, “Fingerprint Matching Techniques using Wavelet Analysis”.
• Marjory Abreu, Michael Fairhurst, “An Empirical Comparison of Individual Machine Learning Techniques in Signature and Fingerprint Classification”.
• Atsushi Sugiura, Yoshiyuki Koseki, “A User Interface Using Fingerprint Recognition – Holding Commands and Data
• Objects on Fingers”, UIST ’98, 1998, ACM, 0-58113-0341/98/11.
• Sung Bum Pan, Youn Hee Gil, Daesung Moon, Yongwha Chung, Chee Hang Park, “A Memory Efficient Fingerprint Verification Algorithm Using a Multi-Resolution Accumulator Array”, ETRI Journal, 2003, Vol. 25(3).
• E. Vonk, L.P.J Veelenturf, L.C. Jain, “Neural Networks: Implementations and Applications”, IEEE AES Magazine, 1996.
• Stainslaw Jankowski, Andrzej Lozowski, Jacek M. Zurada, “Complex Valued Multistate Neural Associative Memory, IEEE Transactions on Neural Networks, 1996, 7(4), 1491 – 1496.
• Yingquan Wu, Dimitris A. Pados, “A Feedforward Bidirectional Associative Memory”, IEEE Transactions on Neural Networks, 2000, Vol. 100(40), 859 – 866.
• Ju Cheng Yang, Sook Yoon, Dong Sun Park, “Applying Learning Vector Quantization Neural Network for Fingerprint Matching”, AI, 2006, LNAI 4304, 500 – 509.
• Ali Okatan, Cagatay Akpolat, Servet Senyucel, “Cosine Transform Method for Fingerprint Recognition”.
• Haijun Zhou, Reinhard Lipowsky, “Dynamic Pattern Evolution on Scale Free Networks”, PNAS, 2005, Vol.102(29), 10052 –10057.
• Jianjiang Feng, Zhengyu Ouyang, Anni Cai, “Fingerprint Matching Using Ridges”, Pattern Recognition, 2006, Vol. 39, 2131 – 2140.
• Amos Storkey, “Increasing the Capacity of a Hopfield Network Without Sacrificing Functionality”, Neural Systems Group, London.
• Sung Jung Hsiao, Kuo Chin Fan, Wen Tsai Sung, Shih ChingOu, “Innovative Algorithms for Running a Web-Based Pattern Recognition Search System for a Component Patterns Database”, Malaysian Journal of Computer Science, 2002, Vol. 15(2), 78 – 93.
• Colin Molter, Utku Salihoglu, Hugues Bersini, “Introduction of a Hebbian Unsupervised Learning Algorithm to Boost the Encoding Capacity of Hopfield Networks”.
• Agnes Meyder, Constantin Kiderlen, “Fundamental Properties of Hopfield NBetworks and Boltzmann Machines for Associative Memories”, Machine Learning, vt 2008.
• B. Yegnanarayana, Artificial Neural Networks.
• 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.
• Dmitry O. Gorodnichy, “The Influence of Self Connection on the Performance of Pseudoinverse Autoassociative Networks”.
• N. Davey, R.G.Adams, “Stochastic Dynamics and High Capacity Associative Memories”.
• M.Brown, J.Austin, “Invariant Pattern Recognition Using Binary Neural Networks”.
• D.M. Titterington, “Bayesian Methods for Neural Networks and Related Models”, Statistical Science, 2004, Vol. 19, No. 1, 128– 139.
• J. Schmidhuber, “Reducing the Ratio Between Learning Complexity and the Number of Time Varyning Variablesin Fully Recurrent Nets”, In Proceedings of the Internationla Conference on Artificial Neural Networks, Amsterdam, pp 460 – 463. Springer, 1993.
• L.F.Abbott, Yair Arian, “Storage Capacity of Generalized Networks”, Rapid Communications, Physical Review A, November 15, 1987, Vol. 36, No. 10, pp 5091 – 5094.
• 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.
• Christophe L. Labiouse, Albert A. Salah, Irina Starikova, “The Impact of Connectivity on the Memory Capacity and the Retrieval Dynamics of Hopfield –type Networks.
• G.Atithan, “A Comparative Study of Two Learning rules for Associative Memory”, PRAMANA – Journal of Physics, December 1995, Vol. 45, No. 6, pp 569 – 582.
• C.J.Perez Vicente, “Hierarchical Neural Network with High Storage Capacity”, Physical Review A, November 1989, Vol. 40, No.9, pp 5356 – 5360.
• J.J.Hopfield, “Neural Networks and Physical Systems with emergent Collective Computational Abilities”, PNAS, 1982, Vol. 79, pp 2554 -2558.
• L.Personnaz, I.Guyon, G.Drefus, “Collective Computational Properties of Neural Networks: New Learning Mechanisms”, Physical Review A, 1986, Vol. 34, No. 5, pp 4217- 4228