Abstract
By simplifying connection topology of Hopfield neural network (HNN) with three neurons, a kind of HNN-based nonlinear system is proposed. Taking a coupling-connection weight as unique adjusting parameter and utilizing conventional dynamical analysis methods, dynamical behaviors with the variation of the adjusting parameter are discussed and coexisting multiple attractors’ behavior under different state initial values are investigated. The results imply that the HNN-based system displays point, periodic, and chaotic behaviors as well as period-doubling and tangent bifurcation routes; particularly, this system exhibits some striking phenomena of coexisting multiple attractors, such as, a pair of single-scroll chaotic attractors accompanied with a pair of periodic attractors, a pair of periodic attractors with two periodicities, and so on. Of particular interest, it should be highly significant that a hardware circuit of the HNN-based system is developed by using commercially available electronic components and many kinds of coexisting multiple attractors are captured from the hardware experiments. The results of the experimental measurements have well consistency to those of MATLAB and PSpice simulations.
Similar content being viewed by others
References
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of 2-state neurons. Proc. Natl. Acad. Sci. USA 81(10), 3088–3092 (1984)
Laskowski, Ł.: A novel hybrid-maximum neural network in stereo-matching process. Neural Comput. Appl. 23(7), 2435–2450 (2013)
Pajeras, G., Cruz, J.M., Aranda, J.: Relaxation by Hopfield network in stereo image matching. Pattern Recognit. 31(5), 561–574 (1998)
Brosch, T., Neumann, H.: Computing with a canonical neural circuits model with pool normalization and modulating feedback. Neural Comput. 26(12), 2735–2789 (2014)
Wen, S., Zeng, Z., Huang, T., Meng, Q., Yao, W.: Lag synchronization of switched neural networks via neural activation function and applications in image encryption. IEEE Trans. Neural Netw. Learn. Syst. 26(7), 1493–1502 (2015)
Yang, J., Wang, L.D., Wang, Y., Guo, T.T.: A novel memristive Hopfield neural network with application in associative memory. Neurocomputing 227, 142–148 (2017)
Trejo-Guerra, R., Tlelo-Cuautle, E., Carbajal-Gómez, V.H., Rodriguez-Gómez, G.: A survey on the integrated design of chaotic oscillators. Appl. Math. Comput. 219(10), 5113–5122 (2013)
Bao, B.C., Li, Q.D., Wang, N., Xu, Q.: Multistability in Chua’s circuit with two stable node-foci. Chaos 26(4), 043111 (2016)
Chen, M., Xu, Q., Lin, Y., Bao, B.C.: Multistability induced by two symmetric stable node-foci in modified canonical Chua’s circuit. Nonlinear Dyn. 87(2), 789–802 (2017)
Biswas, D., Karmakar, B., Banerjee, T.: A hyperchaotic time-delayed system with single-humped nonlinearity: theory and experiment. Nonlinear Dyn. 89(3), 1733–1743 (2017)
Biswas, D., Banerjee, T.: A simple chaotic and hyperchaotic time-delay system: design and electronic circuit implementation. Nonlinear Dyn. 83(4), 2331–2347 (2016)
Banerjee, T., Biswas, D., Sarkar, B.C.: Design and analysis of a first order time-delayed chaotic system. Nonlinear Dyn. 70(1), 721–734 (2012)
Banerjee, T., Biswas, D.: Theory and experiment of a first-order chaotic delay dynamical system. Int. J. Bifurcat. Chaos 23, 1330020 (2013)
Ren, G.D., Xu, Y., Wang, C.N.: Synchronization behavior of coupled neuron circuits composed of memristors. Nonlinear Dyn. 88(2), 893–901 (2017)
Zheng, P.S., Tang, W.S., Zhang, J.X.: Some novel double-scroll chaotic attractors in Hopfield networks. Neurocomputing 73, 2280–2285 (2010)
Yang, X.S., Huang, Y.: Complex dynamics in simple Hopfield neural networks. Chaos 16, 033114 (2006)
Li, Q.D., Tang, S., Zeng, H.Z., Zhou, T.T.: On hyperchaos in a small memristive neural network. Nonlinear Dyn. 78(2), 1087–1099 (2014)
Zheng, P.S., Tang, W.S., Zhang, J.X.: Dynamic analysis of unstable Hopfield networks. Nonlinear Dyn. 61(3), 399–406 (2010)
Rech, P.C.: Period-adding and spiral organization of the periodicity in a Hopfield neural network. Int. J. Mach. Learn. Cybern. 6(1), 1–6 (2015)
Yuan, Q., Li, Q.D., Yang, X.S.: Horseshoe chaos in a class of simple Hopfield neural networks. Chaos Solitons Fractals 39(4), 1522–1529 (2009)
Li, Q.D., Tang, S., Zeng, H.Z., Zhou, T.T.: On hyperchaos in a small memristive neural network. Nonlinear Dyn. 78(2), 1087–1099 (2014)
Pham, V.T., Jafari, S., Vaidyanathan, S., Volos, C.K., Wang, X.: A novel memristive neural network with hidden attractors and its circuitry implementation. Sci. China Technol. Sci. 59, 358–363 (2016)
Bersini, H., Sener, P.: The connections between the frustrated chaos and the intermittency chaos in small Hopfield networks. Neural Netw. 15(10), 1197–1204 (2002)
Babloyantz, A., Lourenco, C.: Brain chaos and computation. Int. J. Neural Syst. 7(4), 461–471 (1996)
Korn, H., Faure, P.: Is there chaos in the brain? II. Experimental evidence and related models. C. R. Biol. 326(9), 787–840 (2003)
Xu, Q., Lin, Y., Bao, B.C., Chen, M.: Multiple attractors in a non-ideal active voltage-controlled memristor based Chua’s circuit. Chaos Solitons Fractals 83, 186–200 (2016)
Bao, B.C., Jiang, T., Xu, Q., Chen, M., Hu, H.G., Hu, Y.H.: Coexisting infinitely many attractors in active band-pass filter-based memristive circuit. Nonlinear Dyn. 86(3), 1711–1723 (2016)
Njitacke, Z.T., Kengne, J., Fotsin, H.B., Negou, A.N., Tchiotsop, D.: Coexistence of multiple attractors and crisis route to chaos in a novel memristive diode bridge-based Jerk circuit. Chaos Solitons Fractals 91, 180–197 (2016)
Bao, B.C., Qian, H., Xu, Q., Chen, M., Wang, J., Yu, Y.J.: Coexisting behaviors of asymmetric attractors in hyperbolic-type memristor based Hopfield neural network. Front. Comput. Neurosci 11, 1–14 (2017). Article 81
Zhusubaliyev, Z.T., Mosekilde, E., Rubanov, V.G., Nabokov, R.A.: Multistability and hidden attractors in a relay system with hysteresis. Physica D 306, 6–15 (2015)
Zhusubaliyev, Z.T., Mosekilde, E.: Multistability and hidden attractors in a multilevel DC/DC converter. Math. Comput. Simul. 109, 32–45 (2015)
Liu, Y.G., You, Z.S.: Multi-stability and almost periodic solutions of a class of recurrent neural networks. Chaos Solitons Fractals 33(2), 554–563 (2007)
Bao, G., Zeng, Z.: Multistability of periodic delayed recurrent neural network with memristors. Neural Comput. Appl. 23(7), 1963–1967 (2013)
Ma, J., Wu, F.G., Ren, G.D., Tang, J.: A class of initials-dependent dynamical systems. Appl. Math. Comput. 298, 65–76 (2017)
Geltrude, A., Al-Naimee, K., Euzzor, S., Meucci, R., Arecchi, F.T., Goswami, B.K.: Feedback control of bursting and multistability in chaotic systems. Coummun. Nonlinear Sci. Numer. Simul. 17(7), 3031–3039 (2012)
Li, C.B., Sprott, J.C.: Coexisting hidden attractors in a 4-D simplified Lorenz system. Int. J. Bifurcat. Chaos 24(3), 1450034 (2014)
Bao, B.C., Bao, H., Wang, N., Chen, M., Xu, Q.: Hidden extreme multistability in memristive hyperchaotic system. Chaos Solitons Fractals 94, 102–111 (2017)
Sprott, J.C., Wang, X., Chen, G.R.: Coexistence of point, periodic and strange attractors. Int. J. Bifurcat Chaos 23(5), 1350093 (2013)
Pisarchik, A.N., Feudel, U.: Control of multistability. Phys. Rep. 540(4), 167–218 (2014)
Li, C.B., Sprott, J.C.: Multistability in the Lorenz system: a broken butterfly. Int. J. Bifurcat Chaos 24(10), 1450131 (2014)
Sharma, P.R., Shrimali, M.D., Prasad, A., Kuznetsov, N.V., Leonov, G.A.: Control of multistability in hidden attractors. Eur. Phys. J. Spec. Top. 224, 1485–1491 (2015)
Shabunin, A.V.: Controlling phase multistability in coupled period-doubling oscillators. Chaos 23(1), 013102 (2013)
Morfu, S., Nofiele, B., Marquié, P.: On the use of multistability for image processing. Phys. Lett. A 367, 192–198 (2007)
Hu, X.Y., Liu, C.X., Liu, L., Ni, J.K., Li, S.L.: An electronic implementation for Morris Lecar neuron model. Nonlinear Dyn. 84(4), 2317–2332 (2016)
Duan, S.K., Liao, X.F.: An electronic implementation for Liao’s chaotic delayed neuron model with non-monotonous activation function. Phys. Lett. A 369, 37–43 (2007)
Wolf, A., Swift, J.B., Swinney, H.L., Vastano, J.A.: Determining Lyapunov exponents from a time series. Physica D 16(3), 285–317 (1985)
Tlelo-Cuautle, E., Rangel-Magdaleno, J.J., Gerardo, D.L.F.L.: Engineering Applications of FPGAs: Chaotic Systems, Artificial Neural Networks, Random Number Generators, and Secure Communication Systems. Springer, Berlin (2016)
Tlelo-Cuautle, E., Rangel-Magdaleno, J.J., Pano-Azucena, A.D., Obeso-Rodelo, P.J., Nunez-Perez, J.C.: FPGA realization of multi-scroll chaotic oscillators. Commun. Nonlinear Sci. Numer. Simul. 27(1–3), 66–80 (2015)
Patel, M.S., Patel, U., Sen, A., Sethia, G.C., Hens, C., Dana, S.K., Feudel, U., Showalter, K., Ngonghala, C.N., Amritkar, R.E.: Experimental observation of extreme multistability in an electronic system of two coupled Rössler oscillators. Phys. Rev. E 89, 022918 (2014)
Biswas, D., Banerjee, T., Kurths, J.: Control of birhythmicity through conjugate self-feedback: theory and experiment. Phys. Rev. E 94, 042226 (2016)
Kuznetsov, N.V., Leonov, G.A., Yuldashev, M.V., Yuldashev, R.V.: Hidden attractors in dynamical models of phase-locked loop circuits: limitations of simulation in MATLAB and SPICE. Commun. Nonlinear Sci. Numer. Simul. 51, 39–49 (2017)
Muñoz-Pacheco, J.M., Tlelo-Cuautle, E., Toxqui-Toxqui, I., Sánchez-López, C., Trejo-Guerra, R.: Frequency limitations in generating multi-scroll chaotic attractors using CFOAs. Int. J. Electron. 101(11), 1559–1569 (2014)
Acknowledgements
This work was supported by the grants from the National Natural Science Foundations of China under Grant Nos. 51777016, 61705021, 61601062, 11602035, and 51607013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bao, B., Qian, H., Wang, J. et al. Numerical analyses and experimental validations of coexisting multiple attractors in Hopfield neural network. Nonlinear Dyn 90, 2359–2369 (2017). https://doi.org/10.1007/s11071-017-3808-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-017-3808-3