An memristor-based synapse implementation using BCM learning rule

被引：31

作者：

Huang, Yongchuang ^{[1
]}

Liu, Junxiu ^{[1
]}

Harkin, Jim ^{[2
]}

McDaid, Liam ^{[2
]}

Luo, Yuling ^{[1
]}

机构：

[1] Guangxi Normal Univ, Sch Elect Engn, Guilin, Peoples R China

[2] Ulster Univ, Sch Comp Engn & Intelligent Syst, Derry BT48 7JL, Londonderry, North Ireland

来源：

NEUROCOMPUTING | 2021年 / 423卷

基金：

中国国家自然科学基金;

关键词：

Memristor; BCM theory; Spiking neural networks; Learning rule; RATE-DEPENDENT PLASTICITY; STABILITY;

D O I：

10.1016/j.neucom.2020.10.106

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel memristive synapse model based on the HP memristor is proposed in this paper, which can address the problem of synaptic weight infinite modulations. The sliding threshold mechanism of the Bienenstock-Cooper-Munro rule (BCM) is used to redefine the memristance (i.e. synaptic weight) adjustment process of the memristive synapse model. Based on the proposed memristor-based synapse and Leaky Integrate-and-Fire neurons, a spiking neural network (SNN) hardware fragment is constructed, where spike trains with different frequencies are used to evaluate the stability performance of the proposed SNN hardware. Results show that compared to other approaches, the network is stable under different stimuli due to the characteristics of the memristor-based synapse model, and prove that the proposed synapse model is able to mimic biological synaptic behaviour and the problem of synaptic weight infinite modulations is addressed. (C) 2020 Elsevier B.V. All rights reserved.

引用

页码：336 / 342

页数：7

共 36 条

[1] Metaplasticity: The plasticity of synaptic plasticity [J].

Abraham, WC ;

Bear, MF .

TRENDS IN NEUROSCIENCES, 1996, 19 (04) :126-130

[2] Presentation of a new hybrid approach for forecasting economic growth using artificial intelligence approaches [J].

Ahmadi, Mohsen ;

Jafarzadeh-Ghoushchi, Saeid ;

Taghizadeh, Rahim ;

Sharifi, Abbas .

NEURAL COMPUTING & APPLICATIONS, 2019, 31 (12) :8661-8680

[3] THEORY FOR THE DEVELOPMENT OF NEURON SELECTIVITY - ORIENTATION SPECIFICITY AND BINOCULAR INTERACTION IN VISUAL-CORTEX [J].

BIENENSTOCK, EL ;

COOPER, LN ;

MUNRO, PW .

JOURNAL OF NEUROSCIENCE, 1982, 2 (01) :32-48

[4] Hebbian Learning in Spiking Neural Networks With Nanocrystalline Silicon TFTs and Memristive Synapses [J].

Cantley, Kurtis D. ;

Subramaniam, Anand ;

Stiegler, Harvey J. ;

Chapman, Richard A. ;

Vogel, Eric M. .

IEEE TRANSACTIONS ON NANOTECHNOLOGY, 2011, 10 (05) :1066-1073

[5]

Cooper L.N., 2004, Theory of cortical plasticity, DOI DOI 10.1142/5462

[6] OPINION The BCM theory of synapse modification at 30: interaction of theory with experiment [J].

Cooper, Leon N. ;

Bear, Mark F. .

NATURE REVIEWS NEUROSCIENCE, 2012, 13 (11) :798-810

[7] Analog Memristive Synapse in Spiking Networks Implementing Unsupervised Learning [J].

Covi, Erika ;

Brivio, Stefano ;

Serb, Alexander ;

Prodromakis, Themis ;

Fanciulli, Marco ;

Spiga, Sabina .

FRONTIERS IN NEUROSCIENCE, 2016, 10

[8] Maintaining the stability of neural function: A homeostatic hypothesis [J].

Davis, GW ;

Bezprozvanny, I .

ANNUAL REVIEW OF PHYSIOLOGY, 2001, 63 :847-869

[9] Sliding Threshold of Spike-Rate Dependent Plasticity of a Semiconducting Polymer/Electrolyte Cell [J].

Dong, Wenshuai ;

Zeng, Fei ;

Hu, Yuandong ;

Chang, Chiating ;

Li, Xiaojun ;

Pan, Feng ;

Li, Guoqi .

JOURNAL OF POLYMER SCIENCE PART B-POLYMER PHYSICS, 2016, 54 (23) :2412-2417

[10] Application of gene expression programming and sensitivity analyses in analyzing effective parameters in gastric cancer tumor size and location [J].

Dorosti, Shadi ;

Ghoushchi, Saeid Jafarzadeh ;

Sobhrakhshankhah, Elham ;

Ahmadi, Mohsen ;

Sharifi, Abbas .

SOFT COMPUTING, 2020, 24 (13) :9943-9964

← 1 2 3 4 →