×

Quasiperiodic-chaotic neural networks and short-term analog memory. (English) Zbl 1462.37101

Summary: A model of quasiperiodic-chaotic neural networks is proposed on the basis of chaotic neural networks. A quasiperiodic-chaotic neuron exhibits quasiperiodic dynamics that an original chaotic neuron does not have. Quasiperiodic and chaotic solutions are exclusively isolated in the parameter space. The chaotic domain can be identified by the presence of a folding structure of an invariant closed curve. Using the property that the influence of perturbation is conserved in the quasiperiodic solution, we demonstrate short-term visual memory in which real numbers are acceptable for representing colors. The quasiperiodic solution is sensitive to dynamical noise when images are restored. However, the quasiperiodic synchronization among neurons can reduce the influence of noise. Short-term analog memory using quasiperiodicity is important in that it can directly store analog quantities. The quasiperiodic-chaotic neural networks are shown to work as large-scale analog storage arrays. This type of analog memory has potential applications to analog computation such as deep learning.

MSC:

37N25 Dynamical systems in biology
37D45 Strange attractors, chaotic dynamics of systems with hyperbolic behavior
92B20 Neural networks for/in biological studies, artificial life and related topics
Full Text: DOI

References:

[1] Adachi, M. & Aihara, K. [1997] “ Associative dynamics in a chaotic neural network,” Neural Netw.10, 83-98. · Zbl 1423.68396
[2] Aihara, K., Matsumoto, G. & Ichikawa, M. [1985] “ An alternating periodic-chaotic sequence observed in neural oscillators,” Phys. Lett. A111, 251-255.
[3] Aihara, K., Numajiri, T., Matsumoto, G. & Kotani, M. [1986] “ Structures of attractors in periodically forced neural oscillators,” Phys. Lett. A116, 313-317.
[4] Aihara, K., Takabe, T. & Toyoda, M. [1990] “ Chaotic neural networks,” Phys. Lett. A144, 333-340.
[5] Amari, S.-I. [1972] “ Learning patterns and pattern sequences by self-organizing nets of threshold elements,” IEEE Trans. Comput.100, 1197-1206. · Zbl 0245.94024
[6] Ambrogio, S., Narayanan, P., Tsai, H., Shelby, R. M., Boybat, I., Di Nolfo, C., Sidler, S., Giordano, M., Bodini, M., Farinha, N. C., Killeen, B., Cheng, C., Jaoudi, Y. & Burr, G. W. [2018] “ Equivalent-accuracy accelerated neural-network training using analogue memory,” Nature558, 60-67.
[7] Anderson, J. A. [1972] “ A simple neural network generating an interactive memory,” Math. Biosci.14, 197-220. · Zbl 0255.92001
[8] Aronson, D. G., Chory, M. A., Hall, G. R. & McGehee, R. P. [1982] “ Bifurcations from an invariant circle for two-parameter families of maps of the plane: A computer-assisted study,” Commun. Math. Phys.83, 303-354. · Zbl 0499.70034
[9] Caianiello, E. [1961] “ Outline of a theory of thought-processes and thinking machines,” J. Theoret. Biol.1, 204-235.
[10] Feigenbaum, M. J., Kadanoff, L. P. & Shenker, S. J. [1982] “ Quasiperiodicity in dissipative systems: A renormalization group analysis,” Physica D5, 370-386.
[11] Fujisaka, H. & Yamada, T. [1983] “ Stability theory of synchronized motion in coupled-oscillator systems,” Progr. Theoret. Phys.69, 32-47. · Zbl 1171.70306
[12] Garfinkel, A., Chen, P. S., Walter, D. O., Karagueuzian, H. S., Kogan, B., Evans, S. J., Karpoukhin, M., Hwang, C., Uchida, T., Gotoh, M., Nwasokwa, O., Sager, P. & Weiss, J. N. [1997] “ Quasiperiodicity and chaos in cardiac fibrillation,” J. Clin. Invest.99, 305-314.
[13] Harris, K. D., Henze, D. A., Hirase, H., Leinekugel, X., Dragoi, G., Czurkó, A. & Buzsáki, G. [2002] “ Spike train dynamics predicts theta-related phase precession in hippocampal pyramidal cells,” Nature417, 738-741.
[14] Hasegawa, M., Ikeguchi, T. & Aihara, K. [2000] “ Exponential and chaotic neurodynamical tabu searches for quadratic assignment problems,” Contr. Cybernet.29, 772-788. · Zbl 0983.90078
[15] Hata, M. [1982] “ Dynamics of Caianiello’s equation,” J. Math. Kyoto Univ.22, 155-173. · Zbl 0502.39005
[16] Horio, Y. & Suyama, K. [1993] “ Switched-capacitor chaotic neuron for chaotic neural networks,” IEEE Int. Symp. Circuits and Systems, Vol. 2, pp. 1018-1021.
[17] Horio, Y., Ichinose, N. & Ogawa, M. [2018] “ Experimental verification of quasi-periodic-orbit stabilization using a switched-capacitor chaotic neural network circuit,” Nonlin. Th. Its Appl. IEICE9, 218-230.
[18] Ichinose, N., Horio, Y. & Ogawa, M. [2018] “ Statistical test of quasiperiodicity in the presence of dynamical noise,” Nonlin. Th. Its Appl. IEICE9, 231-242.
[19] Ito, D., Ueta, T., Kousaka, T. & Aihara, K. [2016] “ Bifurcation analysis of the Nagumo-Sato model and its coupled systems,” Int. J. Bifurcation and Chaos26, 1630006-1-11. · Zbl 1336.37042
[20] Judd, K. [1994] “ Estimating dimension from small samples,” Physica D71, 421-429. · Zbl 0809.62019
[21] Kiernan, M. C., Mogyoros, I. & Burke, D. [1996] “ Differences in the recovery of excitability in sensory and motor axons of human median nerve,” Brain119, 1099-1105.
[22] Kohonen, T. [1972] “ Correlation matrix memories,” IEEE Trans. Comput.C-21, 353-359. · Zbl 0232.68027
[23] MacKay, R. [1988] “ A simple proof of Denjoy’s theorem,” Math. Proc. Cambridge Philos. Soc.103, 299-303. · Zbl 0648.57015
[24] Matsumoto, G., Aihara, K., Hanyu, Y., Takahashi, N., Yoshizawa, S. & Nagumo, J.-I. [1987] “ Chaos and phase locking in normal squid axons,” Phys. Lett. A123, 162-166.
[25] Nagumo, J. & Sato, S. [1972] “ On a response characteristic of a mathematical neuron model,” Kybernetik10, 155-164. · Zbl 0235.92001
[26] Nakano, K. [1972] “ Associatron — A model of associative memory,” IEEE Trans. Syst. Man Cybernet.SMC-2, 380-388.
[27] O’Keefe, J. & Dostrovsky, J. [1971] “ The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat,” Brain Res.34, 171-175.
[28] Oku, M. & Aihara, K. [2011] “ Associative dynamics of color images in a large-scale chaotic neural network,” Nonlin. Th. Its Appl. IEICE2, 508-521.
[29] Oku, M. & Aihara, K. [2012] “ Numerical analysis of transient and periodic dynamics in single and coupled Nagumo-Sato models,” Int. J. Bifurcation and Chaos22, 1230021-1-15. · Zbl 1270.37028
[30] Pecora, L. M. & Carroll, T. L. [1990] “ Synchronization in chaotic systems,” Phys. Rev. Lett.64, 821-824. · Zbl 0938.37019
[31] Reddy, P. R., Amarnadh, V. & Bhaskar, M. [2012] “ Evaluation of stopping criterion in contour tracing algorithms,” Int. J. Comput. Sci. Inform. Technol.3, 3888-3894.
[32] Ruelle, D. & Takens, F. [1971] “ On the nature of turbulence,” Commun. Math. Phys.20, 167-192. · Zbl 0223.76041
[33] Sacker, R. J. [2009] “ Introduction to the 2009 re-publication of the ‘Neimark-Sacker bifurcation theorem’,” J. Diff. Eqs. Appl.15, 753-758. · Zbl 1187.37030
[34] Seliger, H. H. [2002] “ Measurement of memory of color,” Color Res. Appl.27, 233-242.
[35] Shenker, S. J. [1982] “ Scaling behavior in a map of a circle onto itself: Empirical results,” Physica D5, 405-411.
[36] Skaggs, W. E., McNaughton, B. L., Wilson, M. A. & Barnes, C. A. [1996] “ Theta phase precession in hippocampal neuronal populations and the compression of temporal sequences,” Hippocampus6, 149-172.
[37] Yamada, T. & Aihara, K. [1997] “ Nonlinear neurodynamics and combinatorial optimization in chaotic neural networks,” J. Intell. Fuzzy Syst.5, 53-68.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.