Principles of analog neuromorphic computing: from components to systems and algorithms

Abstract

This report presents the current state of affairs in the implementation of artificial intelligence hardware accelerators based on practically successful neural network algorithms of the first and second generations based on formal artificial neural networks (ANNs). The shortcomings of existing solutions are noted and ways to overcome them using analog neuromorphic architectures are outlined.

The latter are created on the principles of the structuring and functioning of a living nervous system, using artificial neurons and models of synaptic contacts - the so–called memristors, electrically rewritable nanoscale elements of non-volatile memory [1-3]. With the use of these elements, it is possible to significantly increase the performance and energy efficiency of algorithm accelerators based on the ANNs [4-6], as well as the formation of promising computing systems based on bioplausible 3rd generation neural network algorithms - Spiking Neural Networks (SNNs) [7-9].

The original method of substantiating the optimal rules for local tuning SNNs with frequency encoding and the possibility of their implementation in the form of the Spike-Timing-Dependent Plasicity (STDP) are discussed [10]. The results of SNN learning stability to a variability of analog memristors, as well as the use of noise as a constructive factor in the fine-tuning and maintenance of SNN memristive weights are demonstrated [7, 11].

Also, approaches to the implementation of local plasticity rules with dopamine-like modulation as a type of SNN reinforcement learning are discussed. The latter is necessary for the formation of imitative "needs" of an agent in the process of its autonomous functioning [12, 13, 14]. The first results on the creation of a prototype of a memristive implantable neuroprosthesis of the motor activity are considered [15, 16].

Finally, possible hardware solutions for both neuronal elements and synaptic connections based on suitable memristive devices are demonstrated. The concept and first results on the creation of an analog neuromorphic computing system based on the above components are presented.

Thus, an attempt is made to systematize the existing and original methods of implementing energy-efficient and compact analog neuromorphic computing systems for real-time and life-learning artificial intelligence.

Keywords

neuromorphic computing / memristor / spiking neural networks / STDP / unsupervised learning / dopamine-like reinforcement learning / neurohybrid systems

References

[1] Strukov D, Snider G, Stewart D, Williams R. The missing memristor found. Nature. 2008;453(7191):80–83. Corrected and republished from: Nature. 2009;459(7250):1154. doi: 10.1038/nature06932

[2] Strukov D., Snider G., Stewart D., Williams R. The missing memristor found // Nature. 2008. Vol. 453, N 7191. P. 80–83. doi: 10.1038/nature06932

[3] Martyshov MN, Emelyanov AV, Demin VA, et al. Multifilamentary character of anticorrelated capacitive and resistive switching in memristive structures based on (Co-Fe-B)x(LiNbO3)100−x nanocomposite. Phys Rev Applied. 2020;14:034016.

[4] Martyshov M.N., Emelyanov A.V., Demin V.A., et al. Multifilamentary character of anticorrelated capacitive and resistive switching in memristive structures based on (Co-Fe-B)x(LiNbO3)100−x nanocomposite // Phys Rev Applied. 2020. Vol. 14. P. 034016.

[5] Minnekhanov AA, Emelyanov AV, Lapkin DA, et al. Parylene-based memristive devices with multilevel resistive switching for neuromorphic applications. Sci Rep. 2019;9(1):10800. doi: 10.1038/s41598-019-47263-9

[6] Minnekhanov A.A., Emelyanov AV., Lapkin D.A., et al. Parylene-based memristive devices with multilevel resistive switching for neuromorphic applications // Sci Rep. 2019. Vol. 9, N 1. P. 10800. doi: 10.1038/s41598-019-47263-9

[7] Prezioso M, Merrikh-Bayat F, Hoskins BD, et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature. 2015;521(7550):61–64. doi: 10.1038/nature14441

[8] Prezioso M., Merrikh-Bayat F., Hoskins B.D., et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors // Nature. 2015. Vol. 521, N 7550. P. 61–64. doi: 10.1038/nature14441

[9] Emelyanov AV, Lapkin DA, Demin VA, Erokhin VV. First steps towards the realization of a double layer perceptron based on organic memristive devices. AIP Advances. 2016;6(11):111301. doi: 10.1063/1.4966257

[10] Emelyanov A.V., Lapkin D.A., Demin V.A., Erokhin V.V. First steps towards the realization of a double layer perceptron based on organic memristive devices // AIP Advances. 2016. Vol. 6, N 11. P. 111301. doi: 10.1063/1.4966257

[11] Yao P, Wu H, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature. 2020;577(7792):641–646. doi: 10.1038/s41586-020-1942-4

[12] Yao P., Wu H., Gao B., et al. Fully hardware-implemented memristor convolutional neural network // Nature. 2020. Vol. 577, N 7792. P. 641–646. doi: 10.1038/s41586-020-1942-4

[13] Emelyanov AV, Nikiruy KE, Serenko AV, et al. Self-adaptive STDP-based learning of a spiking neuron with nanocomposite memristive weights. Nanotechnology. 2020;31(4):045201. doi: 10.1088/1361-6528/ab4a6d

[14] Emelyanov A.V., Nikiruy K.E., Serenko A.V., et al. Self-adaptive STDP-based learning of a spiking neuron with nanocomposite memristive weights // Nanotechnology. 2020. Vol. 31, N 4. P. 045201. doi: 10.1088/1361-6528/ab4a6d

[15] Wang W, Pedretti G, Milo V, et al. Learning of spatiotemporal patterns in a spiking neural network with resistive switching synapses. Sci Adv. 2018;4(9):eaat4752. doi: 10.1126/sciadv.aat4752

[16] Wang W., Pedretti G., Milo V., et al. Learning of spatiotemporal patterns in a spiking neural network with resistive switching synapses // Sci Adv. 2018. Vol. 4, N 9. P. eaat4752. doi: 10.1126/sciadv.aat4752

[17] Gerasimova SA, Mikhaylov AN, Belov AI, et al. Design of memristive interface between electronic neurons. AIP Conf Proc. 2018;1959(1):090005. doi: 10.1063/1.5034744

[18] Gerasimova S.A., Mikhaylov A.N., Belov A.I., et al. Design of memristive interface between electronic neurons // AIP Conf Proc. 2018. Vol. 1959, N 1. P. 090005. doi: 10.1063/1.5034744

[19] Demin VA, Nekhaev DV, Surazhevsky IA, et al. Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network. Neural Netw. 2021;134:64–75. doi: 10.1016/j.neunet.2020.11.005

[20] Demin V.A., Nekhaev D.V., Surazhevsky I.A., et al. Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network // Neural Netw. 2021. Vol. 134. P. 64–75. doi: 10.1016/j.neunet.2020.11.005

[21] Surazhevsky IA, Demin VA, Ilyasov AI, et al. Noise-assisted persistence and recovery of memory state in a memristive spiking neuromorphic network. Chaos, Solitons and Fractals. 2021;146:110890. doi: 10.1016/j.chaos.2021.110890

[22] Surazhevsky I.A., Demin V.A., Ilyasov A.I., et al. Noise-assisted persistence and recovery of memory state in a memristive spiking neuromorphic network // Chaos, Solitons and Fractals. 2021. Vol. 146. P. 110890. doi: 10.1016/j.chaos.2021.110890

[23] Nikiruy KE, Emelyanov AV, Demin VA, et al. Dopamine-like STDP modulation in nanocomposite memristor. AIP Advances. 2019;9(6):065116. doi: 10.1063/1.5111083

[24] Nikiruy K.E., Emelyanov A.V., Demin V.A., et al. Dopamine-like STDP modulation in nanocomposite memristors // AIP Advances. 2019. Vol. 9, N 6. P. 065116. doi: 10.1063/1.5111083

[25] Minnekhanov AA, Shvetsov BS, Emelyanov AV. Parylene-based memristive synapses for hardware neural networks capable of dopamine-modulated STDP learning. J Phys D: Appl Phys. 2021;54(48):484002. doi: 10.1088/1361-6463/ac203c

[26] Minnekhanov A.A., Shvetsov B.S., Emelyanov A.V. Parylene-based memristive synapses for hardware neural networks capable of dopamine-modulated STDP learning // J Phys D: Appl Phys. 2021. Vol. 54, N 48. P. 484002. doi: 10.1088/1361-6463/ac203c

[27] Vlasov D, Rybka R, Sboev A. Reinforcement learning in a spiking neural network with memristive plasticity. In: Reinforcement learning in a spiking neural network with memristive plasticity. 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA); 2022; Kaliningrad, Russian Federation. P. 300–302. doi: 10.1109/DCNA56428.2022.9923314

[28] Vlasov D., Rybka R., Sboev A. Reinforcement learning in a spiking neural network with memristive plasticity // Reinforcement learning in a spiking neural network with memristive plasticity. 6th Scientific School Dynamics of Complex Networks and their Applications (DCNA). 2022. Kaliningrad, Russian Federation. P. 300–302. doi: 10.1109/DCNA56428.2022.9923314

[29] Mikhaylov A, Pimashkin A, Pigareva Y, et al. Neurohybrid memristive CMOS-integrated systems for biosensors and neuroprosthetics. Front Neurosci. 2020;14:358. doi: 10.3389/fnins.2020.00358

[30] Mikhaylov A., Pimashkin A., Pigareva Y., et al. Neurohybrid memristive CMOS-integrated systems for biosensors and neuroprosthetics // Front Neurosci. 2020. Vol. 14. P. 358. doi: 10.3389/fnins.2020.00358

[31] Masaev DN, Suleimanova AA, Prudnikov NV, et al. Memristive circuit-based model of central pattern generator to reproduce spinal neuronal activity in walking pattern. Front Neurosci. 2023;17:1124950. doi: 10.3389/fnins.2023.1124950

[32] Masaev D.N., Suleimanova A.A., Prudnikov N.V., et al. Memristive circuit-based model of central pattern generator to reproduce spinal neuronal activity in walking pattern // Front Neurosci. 2023. Vol. 17. P. 1124950. doi: 10.3389/fnins.2023.1124950

RIGHTS & PERMISSIONS

Eco-Vector