IJMNTA  Vol.8 No.1 , March 2019
Bifurcation Analysis of Reduced Network Model of Coupled Gaussian Maps for Associative Memory
Abstract: This paper proposes an associative memory model based on a coupled system of Gaussian maps. A one-dimensional Gaussian map describes a discrete-time dynamical system, and the coupled system of Gaussian maps can generate various phenomena including asymmetric fixed and periodic points. The Gaussian associative memory can effectively recall one of the stored patterns, which were triggered by an input pattern by associating the asymmetric two-periodic points observed in the coupled system with the binary values of output patterns. To investigate the Gaussian associative memory model, we formed its reduced model and analyzed the bifurcation structure. Pseudo-patterns were observed for the proposed model along with other conventional associative memory models, and the obtained patterns were related to the high-order or quasi-periodic points and the chaotic trajectories. In this paper, the structure of the Gaussian associative memory and its reduced models are introduced as well as the results of the bifurcation analysis are presented. Furthermore, the output sequences obtained from simulation of the recalling process are presented. We discuss the mechanism and the characteristics of the Gaussian associative memory based on the results of the analysis and the simulations conducted.
Cite this paper: Kobayashi, M. and Yoshinaga, T. (2019) Bifurcation Analysis of Reduced Network Model of Coupled Gaussian Maps for Associative Memory. International Journal of Modern Nonlinear Theory and Application, 8, 1-16. doi: 10.4236/ijmnta.2019.81001.

[1]   Minemoto, T., Isokawa, T., Nishimura, H. and Matsui, N. (2017) Pseudo-Orthogonalization of Memory Patterns for Complex-Valued and Quaternionic Associative Memories. Journal of Artificial Intelligence and Soft Computing Research, 7, 257-264.

[2]   Lee, R.S. (2006) Lee-Associator—A Chaotic Auto-Associative Network for Progressive Memory Recalling. Neural Networks, 19, 644-666.

[3]   Kobayashi, M. (2017) Chaotic Pseudo-Orthogonalized Hopfield Associative Memory. Neurocomputing, 241, 147-151.

[4]   Jankowski, S., Lozowski, A. and Zurada, J. (1996) Complex-Valued Multistate Neural Associative Memory. IEEE Transactions on Neural Networks, 7, 1491-1496.

[5]   Hopfield, J.J. (1982) Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of the National Academy of Sciences of the United States of America, 79, 2554-2558.

[6]   Kosko, B. (1988) Bidirectional Associative Memories. IEEE Transactions on Systems, Man and Cybernetics, 18, 49-60.

[7]   Hagiwara, M. (1990) Multidirectional Associative Memory. Proceedings of International Joint Conference on Neural Networks, 1, 3-6.

[8]   Hattori, M. and Hagiwara, M. (1995) Knowledge Processing System Using Multidirectional Associative Memory. Proceedings of IEEE International Conference on Neural Network, 1, 1304-1309.

[9]   Huang, J. and Hagiwara, M. (2002) A Combinedmulti-Winner Multidirectional Associative Memory. Neurocomputing, 48, 369-389.

[10]   Adachi, M. and Aihara, K. (1997) Associative Dynamics in a Chaotic Neural Network. Neural Networks, 10, 83-98.

[11]   Patidar, V. (2006) Co-Existence of Regular and Chaotic Motions in the Gaussian Map. Electronic Journal of Theoretical Physics, 3, 29-40.

[12]   Patidar, V. and Sud, K. (2009) A Comparative Study on the Co-Existing Attractors in the Gaussian Map and Its Q-Deformed Version. Communications in Nonlinear Science and Numerical Simulation, 14, 827-838.

[13]   Hilborn, R.C. (2000) Chaos and Nonlinear Dynamics: An Introduction for Scientists and Engineers. 2nd Edition, Oxford University Press, Oxford.

[14]   Kawakami, H. (1984) Bifurcation of Periodic Responses in Forced Dynamic Nonlinear Circuits: Computation of Bifurcation Values of the System Parameters. IEEE Transactions on Circuits and Systems, 31, 248-260.