Gate tunable MoS₂ memristive neuron for early fusion of visual and acoustic signals spiking neural network

Abstract

Neuromorphic computing systems, inspired by the brain's parallel processing capabilities and efficiency, offer promising solutions for artificial intelligence. Spiking neural networks (SNNs), composed of neuron and synapse elements, are a key approach for neuromorphic systems. However, traditional hardware neuron implementations require auxiliary circuits to achieve good training performance of SNNs. Developing appropriate single-device based neural components to enable efficient SNN implementations remains elusive. Here, we introduce a gate tunable MoS₂ memristive neuron. This neuron possesses tunable refractory periods and firing thresholds, emulating key dynamics of neurons without external circuits. Leveraging these adaptable neurons, we develop an early fusion SNN architecture for multimodal information processing based on tunable neuron devices. Through cross-modality weight sharing, proposed neurons can learn common features across modalities and modality-specific features under different gate voltages. This architecture achieves seamless fusion of multisensory data while significantly reducing hardware costs. We demonstrate a 49% reduction in hardware usage along with a major boost in recognition accuracy to 95.45% on an image-audio digit recognition task. Our tunable neuron-enabled SNN provides a pathway for highly efficient neural computing and further integration of neuromorphic intelligence.

Keywords

memristor / multimodal SNN / neuron

References

[1] Marković D, Mizrahi A, Querlioz D, Grollier J. Physics for neuromorphic computing. Nat Rev Phys. 2020; 2(9): 499-510.

[2] Lee G, Baek J-H, Ren F, Pearton SJ, Lee G-H, Kim J. Artificial neuron and synapse devices based on 2D materials. Small. 2021; 17(20):2100640.

[3] Yang X, Taylor B, Wu A, Chen Y, Chua LO. Research Progress on memristor: from synapses to computing systems. IEEE Trans Circ Syst I Regul Pap. 2022; 69(5): 1845-1857.

[4] Li H, Hu J, Chen A, et al. Single-transistor neuron with excitatory–inhibitory spatiotemporal dynamics applied for neuronal oscillations. Adv Mater. 2022; 34(51):2207371.

[5] Jo SH, Chang T, Ebong I, Bhadviya BB, Mazumder P, Lu W. Nanoscale memristor device as synapse in neuromorphic systems. Nano Lett. 2010; 10(4): 1297-1301.

[6] Sueoka B, Hasan Tanim MM, Williams L, et al. A synaptic memristor based on natural organic honey with neural facilitation. Org Electron. 2022; 109:106622.

[7] Prezioso M, Merrikh-Bayat F, Hoskins BD, Adam GC, Likharev KK, Strukov DB. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature. 2015; 521(7550): 61-64.

[8] Wang Z, Joshi S, Savel'ev SE, et al. Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. Nat Mater. 2017; 16(1): 101-108.

[9] Yi W, Tsang KK, Lam SK, Bai X, Crowell JA, Flores EA. Biological plausibility and stochasticity in scalable VO₂ active memristor neurons. Nat Commun. 2018; 9(1):4661.

[10] Kumar S, Wang X, Strachan JP, Yang Y, Lu WD. Dynamical memristors for higher-complexity neuromorphic computing. Nat Rev Mater. 2022; 7(7): 575-591.

[11] Hao S, Ji X, Zhong S, et al. A monolayer leaky integrate-and-fire neuron for 2D memristive neuromorphic networks. Adv Electron Mater. 2020; 6(4):1901335.

[12] Fu T, Liu X, Gao H, et al. Bioinspired bio-voltage memristors. Nat Commun. 2020; 11(1):1861.

[13] Kang J, Kim T, Hu S, et al. Cluster-type analogue memristor by engineering redox dynamics for high-performance neuromorphic computing. Nat Commun. 2022; 13(1): 4040.

[14] Wang Z, Joshi S, Savel'ev S, et al. Fully memristive neural networks for pattern classification with unsupervised learning. Nat Electron. 2018; 1(2): 137-145.

[15] Wang Y, Xu H, Wang W, et al. A configurable artificial neuron based on a threshold-tunable TiN/NbO_x/Pt memristor. IEEE Electron Device Lett. 2022; 43(4): 631-634.

[16] Guo T, Pan K, Sun B, et al. Adjustable leaky-integrate-and-fire neurons based on memristor-coupled capacitors. Mater Today Adv. 2021; 12:100192.

[17] Midya R, Wang Z, Asapu S, et al. Artificial neural network (ANN) to spiking neural network (SNN) converters based on diffusive memristors. Adv Electron Mater. 2019; 5(9):1900060.

[18] Xu W, Wang J, Yan X. Advances in memristor-based neural networks. Front in Nanotechnology. 2021; 3:645995.

[19] Wijesinghe P, Ankit A, Sengupta A, Roy K. An all-memristor deep spiking neural computing system: a step toward realizing the low-power stochastic brain. IEEE Trans Emerg Top Comput Intell. 2018; 2(5): 345-358.

[20] Zhang Y, Wang X, Friedman EG. Memristor-based circuit design for multilayer neural networks. IEEE Trans Circ Syst I Regul Pap. 2018; 65(2): 677-686.

[21] Rosenthal E, Greshnikov S, Soudry D, Kvatinsky S. A fully analog memristor-based neural network with online gradient training. 2016 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE; 2016: 1394-1397.

[22] Wang Z, Rao M, Han J-W, et al. Capacitive neural network with neuro-transistors. Nat Commun. 2018; 9(1): 3208.

[23] Xia Q, Yang JJ. Memristive crossbar arrays for brain-inspired computing. Nat Mater. 2019; 18(4): 309-323.

[24] Babacan Y, Kaçar F, Gürkan K. A spiking and bursting neuron circuit based on memristor. Neurocomputing. 2016; 203: 86-91.

[25] Fan D, Shim Y, Raghunathan A, Roy K. STT-SNN: a spin-transfer-torque based soft-limiting non-linear neuron for low-power artificial neural networks. IEEE Trans Nanotechnol. 2015; 14(6): 1013-1023.

[26] Yang R, Li H, Smithe KKH, et al. Ternary content-addressable memory with MoS₂ transistors for massively parallel data search. Nat Electron. 2019; 2(3): 108-114.

[27] Hua Q, Gao G, Jiang C, et al. Atomic threshold-switching enabled MoS₂ transistors towards ultralow-power electronics. Nat Commun. 2020; 11(1):6207.

[28] Hu J, Li H, Zhang Y, et al. Reconfigurable neuromorphic computing with 2D material heterostructures for versatile neural information processing. Nano Lett. 2024; 24(30): 9391-9398.

[29] Mathias B, von Kriegstein K. Enriched learning: behavior, brain, and computation. Trends Cogn Sci. 2023; 27(1): 81-97.

[30] Subbulakshmi Radhakrishnan S, Chakrabarti S, Sen D, et al. A sparse and spike-timing-based adaptive photoencoder for augmenting machine vision for spiking neural networks. Adv Mater. 2022; 34(48):2202535.

[31] Sadaf MUK, Sakib NU, Pannone A, Ravichandran H, Das S. A bio-inspired visuotactile neuron for multisensory integration. Nat Commun. 2023; 14(1): 5729.

[32] Neverova N, Wolf C, Taylor G, Nebout F. ModDrop: adaptive multi-modal gesture recognition. IEEE Trans Pattern Anal Mach Intell. 2016; 38(8): 1692-1706.

[33] Vielzeuf V, Lechervy A, Pateux S, Jurie F. Centralnet: a multilayer approach for multimodal fusion. Proceedings of the European Conference on Computer Vision (ECCV) Workshops; 2018.

[34] Liu Y, Pan Z, Tian H. Reconfigurable logic operation scheme based on gate-tunable CBRAM. IEEE Trans Electron Devices. 2023; 70(1): 88-92.

[35] Wang X-F, Tian H, Liu Y, et al. Two-mode MoS₂ filament transistor with extremely low subthreshold swing and record high on/off ratio. ACS Nano. 2019; 13(2): 2205-2212.

[36] Obermayer J, Luchicchi A, Heistek TS, et al. Prefrontal cortical ChAT-VIP interneurons provide local excitation by cholinergic synaptic transmission and control attention. Nat Commun. 2019; 10(1):5280.

[37] Bushara KO, Weeks RA, Ishii K, et al. Modality-specific frontal and parietal areas for auditory and visual spatial localization in humans. Nat Neurosci. 1999; 2(8): 759-766.

[38] Zhang M, Luo X, Chen Y, et al. An efficient threshold-driven aggregate-label learning algorithm for multimodal information processing. IEEE J Sel Top Signal Process. 2020; 14(3): 592-602.

[39] Yu F, Wu Y, Ma S, et al. Brain-inspired multimodal hybrid neural network for robot place recognition. Sci Robot. 2023; 8(78):eabm6996.

[40] Deng L, Wu Y, Hu X, et al. Rethinking the performance comparison between SNNS and ANNS. Neural Netw. 2020; 121: 294-307.

RIGHTS & PERMISSIONS

2026 The Author(s). InfoMat published by UESTC and John Wiley & Sons Australia, Ltd.