Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors

Song, Lekai1; Liu, Pengyu1; Pei, Jingfang1; Bai, Fan1; Liu, Yang1,2; Liu, Songwei1; Wen, Yingyi1; Ng, Leonard W. T.3; Pun, Kong-Pang1; Gao, Shuo4; Meng, Max Q. -H.5; Hasan, Tawfique6; Hu, Guohua1

2023-10-01

10.1002/aelm.202300564

ADVANCED ELECTRONIC MATERIALS   Impact Factor & Quartile

2199-160X

Implementing and integrating spiking neurons for neuromorphic hardware realization conforming to spiking neural networks holds great promise in enabling efficient learning and decision-making. The spiking neurons, however, may lack the spiking dynamics to encode the dynamical information in complex real-world problems. Herein, using filamentary memristors from solution-processed hexagonal boron nitride, this study assembles leaky integrate-and-fire spiking neurons and, particularly, harnesses the common switching stochasticity feature in the memristors to allow key neural dynamics, including Poisson-like spiking and adaptation. The neurons, with the dynamics fitted via hardware-algorithm codesign, suggest a potential in realizing spike-based neuromorphic hardware capable of handling complex problems. Simulation of an autoencoder for anomaly detection of time-series real analog and digital data from physical systems is demonstrated, underscoring its promising prospect in applications, especially, at the edges with limited computation resources, for instance, auto-pilot, manufacturing, wearables, and Internet of things.

neural spiking dynamics self-reset threshold switching memristors spike-based neuromorphic computing spiking neurons switching stochasticity

SCI

English

Others

G.H.H. acknowledges support from RGC (24200521) and SHIAE (RNE-p3-21), YL from SHIAE (RNE-p3-21), JFP and YYW from RGC (24200521), and LWTN from NTU (start-up grant). The authors thank the snnTorch group at the University of Michigan for the snnTorch packa[24200521] ; RGC[RNE-p3-21]

Science & Technology - Other Topics ; Materials Science ; Physics

Nanoscience & Nanotechnology ; Materials Science, Multidisciplinary ; Physics, Applied

WOS:001085458200001

WILEY

Web of Science

1.Chinese Univ Hong Kong, Dept Elect Engn, Shatin, Hong Kong 999077, Peoples R China
2.Chinese Univ Hong Kong, Shun Hing Inst Adv Engn, Shatin, Hong Kong 999077, Peoples R China
3.Nanyang Technol Univ, Sch Mat Sci & Engn, Singapore 639798, Singapore
4.Beihang Univ, Sch Instrumentat & Optoelect Engn, Beijing 100191, Peoples R China
5.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China
6.Univ Cambridge, Cambridge Graphene Ctr, Cambridge CB3 0FA, England

Song, Lekai,Liu, Pengyu,Pei, Jingfang,et al. Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors[J]. ADVANCED ELECTRONIC MATERIALS,2023.

Song, Lekai.,Liu, Pengyu.,Pei, Jingfang.,Bai, Fan.,Liu, Yang.,...&Hu, Guohua.(2023).Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors.ADVANCED ELECTRONIC MATERIALS.

Song, Lekai,et al."Spiking Neurons with Neural Dynamics Implemented Using Stochastic Memristors".ADVANCED ELECTRONIC MATERIALS (2023).