Memristive cyclic three-neuron-based neural network with chaos and global coexisting attractors
Source abstract
Abstract
It has been documented that a cyclic three-neuron-based neural network with resistive synaptic weights cannot exhibit chaos. Towards this end, a memristive cyclic three-neuron-based neural network is presented using a memristive weight to substitute a resistive weight. The memristive cyclic neural network always has five equilibrium points within the parameters of interest, and their stability analysis shows that they are one index-2 saddle-focus, two index-1 saddle-foci, and two stable node-foci, respectively. Dynamical analyses are performed for the memristive cyclic neural network by several numerical simulation methods. The results demonstrate that the memristor synapse-based neural network with the simplest cyclic connection can not only exhibit chaos, but also present global coexisting attractors composed of stable points and unstable periodic or chaotic orbits under different initial conditions. Besides, with the designed implementation circuit, Multisim circuit simulations and hardware experiments are executed to validate the numerical simulations.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Neural dynamics and brain function · stochastic dynamics and bifurcation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Ma J, Tang J. A review for dynamics in neuron and neuronal network. Nonlinear Dyn, 2017, 89: 1569–157810.1007/s11071-017-3565-3 ↗
2. Korn H, Faure P. Is there chaos in the brain? II. Experimental evidence and related models. Comptes Rendus Biol, 2003, 326: 787–84010.1016/j.crvi.2003.09.011 ↗
3. Bao H, Hu A, Liu W, et al. Hidden bursting firings and bifurcation mechanisms in memristive neuron model with threshold electromagnetic induction. IEEE Trans Neural Netw Learn Syst, 2020, 31: 502–51110.1109/TNNLS.2019.2905137 ↗
4. Mondal A, Upadhyay R K, Ma J, et al. Bifurcation analysis and diverse firing activities of a modified excitable neuron model. Cogn Neurodyn, 2019, 13: 393–40710.1007/s11571-019-09526-z ↗
5. Bao H, Hua Z Y, Liu W B, et al. Discrete memristive neuron model and its interspike interval-encoded application in image encryption. Sci China Tech Sci, 2021, 64: 2281–229110.1007/s11431-021-1845-x ↗
6. Wouapi M K, Fotsin B H, Ngouonkadi E B M, et al. Complex bifurcation analysis and synchronization optimal control for Hindmarsh-Rose neuron model under magnetic flow effect. Cogn Neurodyn, 2021, 15: 315–34710.1007/s11571-020-09606-5 ↗
7. Lu L L, Jia Y, Xu Y, et al. Energy dependence on modes of electric activities of neuron driven by different external mixed signals under electromagnetic induction. Sci China Tech Sci, 2019, 62: 427–44010.1007/s11431-017-9217-x ↗
8. Xu Q, Ju Z, Ding S, et al. Electromagnetic induction effects on electrical activity within a memristive Wilson neuron model. Cogn Neurodyn, 2022, 16: 1221–123110.1007/s11571-021-09764-0 ↗
9. Chen M, Qi J W, Wu H G, et al. Bifurcation analyses and hardware experiments for bursting dynamics in non-autonomous memristive FitzHugh-Nagumo circuit. Sci China Tech Sci, 2020, 63: 1035–104410.1007/s11431-019-1458-5 ↗
10. Izhikevich E M. Simple model of spiking neurons. IEEE Trans Neural Netw, 2003, 14: 1569–157210.1109/TNN.2003.820440 ↗
11. Bao B C, Zhu Y X, Ma J, et al. Memristive neuron model with an adapting synapse and its hardware experiments. Sci China Tech Sci, 2021, 64: 1107–111710.1007/s11431-020-1730-0 ↗
12. Xu Q, Ding S, Bao H, et al. Piecewise-linear simplification for adaptive synaptic neuron model. IEEE Trans Circuits Syst II, 2022, 69: 1832–183610.1109/TCSII.2021.3124666 ↗
13. Jin W Y, Wang A, Ma J, et al. Effects of electromagnetic induction and noise on the regulation of sleep wake cycle. Sci China Tech Sci, 2019, 62: 2113–211910.1007/s11431-018-9423-x ↗
14. Bao B, Chen C, Bao H, et al. Dynamical effects of neuron activation gradient on Hopfield neural network: Numerical analyses and hardware experiments. Int J Bifurcation Chaos, 2019, 29: 193001010.1142/S0218127419300106 ↗
15. Chen C, Min F, Zhang Y, et al. Memristive electromagnetic induction effects on Hopfield neural network. Nonlinear Dyn, 2021, 106: 2559–257610.1007/s11071-021-06910-5 ↗
16. Mathias A C, Rech P C. Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions. Neural Networks, 2012, 34: 42–4510.1016/j.neunet.2012.06.006 ↗
17. Lin H, Wang C, Chen C, et al. Neural bursting and synchronization emulated by neural networks and circuits. IEEE Trans Circuits Syst I, 2021, 68: 3397–341010.1109/TCSI.2021.3081150 ↗
18. Njitacke Z T, Isaac S D, Nestor T, et al. Window of multistability and its control in a simple 3D Hopfield neural network: Application to biomedical image encryption. Neural Comput Applic, 2021, 33: 6733–675210.1007/s00521-020-05451-z ↗
19. Njitacke Z T, Kengne J, Fotsin H B. Coexistence of multiple stable states and bursting oscillations in a 4D Hopfield neural network. Circuits Syst Signal Process, 2020, 39: 3424–344410.1007/s00034-019-01324-6 ↗
20. Pu Y F, Yi Z, Zhou J L. Fractional Hopfield neural networks: Fractional dynamic associative recurrent neural networks. IEEE Trans Neural Netw Learn Syst, 2017, 28: 2319–233310.1109/TNNLS.2016.2582512 ↗
21. Kobayashi M. Diagonal rotor Hopfield neural networks. Neurocomputing, 2020, 415: 40–4710.1016/j.neucom.2020.07.041 ↗
22. Danca M F, Kuznetsov N. Hidden chaotic sets in a Hopfield neural system. Chaos Solitons Fractals, 2017, 103: 144–15010.1016/j.chaos.2017.06.002 ↗
23. Balasubramonian M, Rajamani V. Design and real-time implementation of SHEPWM in single-phase inverter using generalized Hopfield neural network. IEEE Trans Ind Electron, 2014, 61: 6327–633610.1109/TIE.2014.2304919 ↗
24. Wang P, Wang L, Leung H, et al. Subpixel mapping based on Hopfield neural network with more prior information. IEEE Geosci Remote Sens Lett, 2019, 16: 1284–128810.1109/LGRS.2019.2895629 ↗
25. Lehtonen E, Poikonen J H, Laiho M, et al. Large-scale memristive associative memories. IEEE Trans VLSI Syst, 2014, 22: 562–57410.1109/TVLSI.2013.2250319 ↗
26. Guo M, Zhu Y, Liu R, et al. An associative memory circuit based on physical memristors. Neurocomputing, 2022, 472: 12–2310.1016/j.neucom.2021.11.034 ↗
27. Pham V T, Jafari S, Vaidyanathan S, et al. A novel memristive neural network with hidden attractors and its circuitry implementation. Sci China Tech Sci, 2016, 59: 358–36310.1007/s11431-015-5981-2 ↗
28. Bao B, Qian H, Xu Q, et al. Coexisting behaviors of asymmetric attractors in hyperbolic-type memristor based Hopfield neural network. Front Comput Neurosci, 2017, 11: 8110.3389/fncom.2017.00081 ↗
29. Lin H, Wang C, Hong Q, et al. A multi-stable memristor and its application in a neural network. IEEE Trans Circuits Syst II, 2020, 67: 3472–347610.1109/TCSII.2020.3000492 ↗
30. Cai F, Kumar S, Van Vaerenbergh T, et al. Power-efficient combinatorial optimization using intrinsic noise in memristor Hopfield neural networks. Nat Electron, 2020, 3: 409–41810.1038/s41928-020-0436-6 ↗
31. Hu S G, Liu Y, Liu Z, et al. Associative memory realized by a reconfigurable memristive Hopfield neural network. Nat Commun, 2015, 6: 752210.1038/ncomms8522 ↗
32. Chen C, Chen J, Bao H, et al. Coexisting multi-stable patterns in memristor synapse-coupled Hopfield neural network with two neurons. Nonlinear Dyn, 2019, 95: 3385–339910.1007/s11071-019-04762-8 ↗
33. Yang X S. 3-D cellular neural networks with cyclic connections cannot exhibit chaos. Int J Bifurcation Chaos, 2008, 18: 1227–123010.1142/S0218127408020951 ↗
34. Yang X S, Yuan Q. Chaos and transient chaos in simple Hopfield neural networks. Neurocomputing, 2005, 69: 232–24110.1016/j.neucom.2005.06.005 ↗
35. Yang X S, Huang Y. Complex dynamics in simple Hopfield neural networks. Chaos, 2006, 16: 03311410.1063/1.2220476 ↗
36. Lai Q, Lai C, Kuate P D K, et al. Chaos in a simplest cyclic memristive neural network. Int J Bifurcation Chaos, 2022, 32: 225004210.1142/S0218127422500420 ↗
37. Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA, 1984, 81: 3088–309210.1073/pnas.81.10.3088 ↗
38. Chen C, Bao H, Chen M, et al. Non-ideal memristor synapse-coupled bi-neuron Hopfield neural network: Numerical simulations and breadboard experiments. AEU-Int J Electron Commun, 2019, 111: 15289410.1016/j.aeue.2019.152894 ↗
39. Singh J P, Roy B K. The simplest 4-D chaotic system with line of equilibria, chaotic 2-torus and 3-torus behaviour. Nonlinear Dyn, 2017, 89: 1845–186210.1007/s11071-017-3556-4 ↗
40. Bao H, Chen M, Wu H G, et al. Memristor initial-boosted coexisting plane bifurcations and its extreme multi-stability reconstitution in two-memristor-based dynamical system. Sci China Tech Sci, 2020, 63: 603–61310.1007/s11431-019-1450-6 ↗
41. Chen M, Xu Q, Lin Y, et al. Multistability induced by two symmetric stable node-foci in modified canonical Chua’s circuit. Nonlinear Dyn, 2017, 87: 789–80210.1007/s11071-016-3077-6 ↗
42. Jiang Y, Huang P, Zhu D, et al. Design and hardware implementation of neuromorphic systems with RRAM synapses and threshold-controlled neurons for pattern recognition. IEEE Trans Circuits Syst I, 2018, 65: 2726–273810.1109/TCSI.2018.2812419 ↗
43. Cai J, Bao H, Xu Q, et al. Smooth nonlinear fitting scheme for analog multiplierless implementation of Hindmarsh-Rose neuron model. Nonlinear Dyn, 2021, 104: 4379–438910.1007/s11071-021-06453-9 ↗
44. Hua M, Yang S, Xu Q, et al. Forward and reverse asymmetric memristor-based jerk circuits. AEU-Int J Electron Commun, 2020, 123: 15329410.1016/j.aeue.2020.153294 ↗
45. Lai Q, Wan Z, Zhang H, et al. Design and analysis of multiscroll memristive hopfield neural network with adjustable memductance and application to image encryption. IEEE Trans Neural Netw Learn Syst, 2022, doi: https://doi.org/10.1109/TNNLS.2022.314657010.1109/TNNLS.2022.3146570 ↗