Abstract
Associative memory in chaotic neural networks differs from traditional associative memory models in their rich dynamics that may lead to promising solutions for a number of information processing problems. In this paper, we propose a new method to control the chaotic neural network, whose refractoriness is tuned by using feedback control based on online averaging of network states. An augmented autoassociative layer is employed to further improve the retrieval performance. Simulation results demonstrate that the proposed chaotic neural network model gives favourable performance in handling noisy, incomplete and composite patterns, while in the meantime achieving either enhanced or comparable memory capacity compared with the conventional Hopfield net and other chaotic neural network models. With the ability to retrieve multiple patterns from memory according to their similarity, it is promising for the proposed network to be applied in real-world information retrieval tasks upon further improvement.
Similar content being viewed by others
References
Adachi M, Aihara K. Associative dynamics in a chaotic neural network. Neural Netw. 1997;8:83–98.
Aihara K. Chaos engineering and its application to parallel distributed processing with chaotic neural networks. Proceedings of IEEE. 2002;90(5):919–30.
Aihara K, Takabe T, Toyoda M. Chaotic neural networks. Phys Lett A. 1990;144:333–40.
Calitoiu D, Oommen BJ. Desynchronizing a chaotic pattern recognition neural network to model inaccurate perception. IEEE Trans. Sys. Man Cybern. Part B. 2007;37:692–704.
Carpenter G, Grossberg S. Adaptive resonance theory (ART). 2nd ed. Cambridge: MIT Press; 2003. p. 79–82.
Chartier S, Renaud P, Boukadoum M. A nonlinear dynamic artificial neural network model of memory. New Ideas Psychol. 2008;26(2):252–77. doi:10.1016/j.newideapsych.2007.07.005 http://www.sciencedirect.com/science/article/B6VD4-4PK8MJ7-1/2/9c68ac243863610954a6d0e0af16a647. Dynamics and Psychology.
Chau M, Chen H. Incorporating web analysis into neural networks: an example in hopfield net searching. IEEE Trans Syst, Man, Cybern, Part C. 2007;37(3):352–8.
Chen L, Aihara K. Chaotic simulated annealing by a neural network model with transient chaos. Neural Netw. 1995;8:915–30.
Deng D. Content-based image collection summarization and comparison using self-organizing maps. Pattern Recognit. 2007;40(2):718–27.
Deng JD, Li S. Improving the pattern retrieval characteristics of the aihara chaotic neural network mode. In: Proceedings of ICITA’08; 2008. p. 732–7.
Hasegawa M, Ikeguchi T, Aihara K. Solving large scale traveling salesman problems by chaotic neurodynamics. Neural Netw. 2002;15(2):271–83. http://dx.doi.org/10.1016/S0893-6080(02)00017-5.
Haykin S. Neural networks: a comprehensive foundation. Prentice Hall: Upper Saddle River; 1999.
He G, Chen L, Aihara K. Associative memory with a controlled chaotic neural network. Neurocomputing 2008;71:2794–805.
He G, Shirimali MD, Aihara K. Threshold control of chaotic neural network. Neural Netw. 2008;21:114–21.
He G, Shrimali MD, Aihara K. Partial state feedback control of chaotic neural networks and its application. Phys Lett A. 2007;371:228–33.
Hopfield JJ. Neural networks and physical systems with emergent collective computation abilities. Proc Nat Acad Sci. 1982;79:2554–8.
Kanamaru T. Chaotic pattern transitions in pulse neural networks. Neural Netw. 2007;20(7):781–90. http://dx.doi.org/10.1016/j.neunet.2007.06.002.
Kohonen T, Schroeder MR, Huang TS, editors. Self-organizing maps. Secaucus: Springer; 2001.
Kosuge S, Osana Y. Chaotic associative memory using distributed patterns for image retrieval by shape information. In: Proceedings of interernational joint conference neural networks (IJCNN) 2004, vol. 2; 2004. p. 903–8.
Kristian Nybo JV, Kaski S. The self-organizing map as a visual information retrieval method. In: Proceedings of WSOM’07, 6th international workshop on self-organizing maps. 2007. http://eprints.pascal-network.org/archive/00003556/.
Lee R. Lee-associator- a chaotic auto-associative network for progressive memory recalling. Neural Netw. 2006;19:644–66.
Lin JS. Annealed chaotic neural network with nonlinear self-feedback and its application to clustering problem. Pattern Recognit 2001;34:1093–104.
Mirzaei A, Safabakhsh R. Optimal matching by the transiently chaotic neural network. Appl Soft Comput. 2009;9(3):863–73. doi:10.1016/j.asoc.2008.07.009.
Park SS, Seo KK, Jang DS. Expert system based on artificial neural networks for content-based image retrieval. Expert Syst Appl 2005;29(3):589–97. doi:10.1016/j.eswa.2005.04.027.
Romero RAF, Vicentini JF, Oliveira PR, Traina AMJ. Investigating the potential of art neural network models for indexing and information retrieval: Research articles. Int J Intell Syst 2007; 22(4):319–36. http://dx.doi.org/10.1002/int.v22:4.
Wolf A, Swift JB, Swinney HL, Vastano JA. Determining Lyapunov exponents from a time series. Physica D: Nonlinear Phenom. 1985;16(3):285–317. doi:10.1016/0167-2789(85)90011-9.
Xiu C, Liu X, Tang Y, Zhang Y. A novel network of chaotic elements and its application in multi-valued associative memory. Phys Lett A. 2004;331:217–24.
Zhao L, Caceres J, Damiance A Jr, Szu H. Chaotic dynamics for multi-value content addressable memory. Neurocomputing 2006;69:1628–36.
Zhao L, Cupertino TH, Bertini JR Jr. Chaotic synchronization in general network topology for scene segmentation. Neurocomputing 2008;71(16-18):3360–6. http://dx.doi.org/10.1016/j.neucom.2008.02.024.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Deng, J.D. Controlling Chaotic Associative Memory for Multiple Pattern Retrieval. Cogn Comput 2, 257–264 (2010). https://doi.org/10.1007/s12559-010-9043-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-010-9043-6