A Low Energy Oxide-Based Electronic Synaptic Device for Neuromorphic Visual Systems with Tolerance to Device Variation

被引：475

作者：

Yu, Shimeng ^{[1
,2
]}

Gao, Bin ^{[3
]}

Fang, Zheng ^{[5
]}

Yu, Hongyu ^{[4
]}

Kang, Jinfeng ^{[3
]}

Wong, H. -S. Philip ^{[1
,2
]}

机构：

[1] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA

[2] Stanford Univ, Ctr Integrated Syst, Stanford, CA 94305 USA

[3] Peking Univ, Inst Microelect, Beijing 100871, Peoples R China

[4] South Univ Sci & Technol China, Shenzhen 518055, Peoples R China

[5] ASTAR, Inst Microelect, Singapore 117685, Singapore

来源：

ADVANCED MATERIALS | 2013年 / 25卷 / 12期

关键词：

resistive switching; oxide RRAM; synaptic devices; neuromorphic computing; artificial visual systems; SWITCHING PARAMETER VARIATION; SPIKING NEURONS; PLASTICITY; SYNAPSES; DESIGN; MEMORY;

D O I：

10.1002/adma.201203680

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

Neuromorphic computing is an emerging computing paradigm beyond the conventional digital von Neumann computation. An oxide-based resistive switching memory is engineered to emulate synaptic devices. At the device level, the gradual resistance modulation is characterized by hundreds of identical pulses, achieving a low energy consumption of less than 1 pJ per spike. Furthermore, a stochastic compact model is developed to quantify the device switching dynamics and variation. At system level, the performance of an artificial visual system on the image orientation or edge detection with 16 348 oxide-based synaptic devices is simulated, successfully demonstrating a key feature of neuromorphic computing: tolerance to device variation. [GRAPHICS] .

引用

页码：1774 / 1779

页数：6

共 31 条

[1] Efficient Hybrid CMOS-Nano Circuit Design for Spiking Neurons and Memristive Synapses with STDP [J].

Afifi, Ahmad ;

Ayatollahi, Ahmad ;

Raissi, Farshid ;

Hajghassem, Hasan .

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2010, E93A (09) :1670-1677

[2]

Ananthanarayanan R., 2009, ACM IEEE C HIGH PERF

[3]

[Anonymous], 1985, VOLUNTARY MOVEMENT

[4] Short-Term Memory to Long-Term Memory Transition in a Nanoscale Memristor [J].

Chang, Ting ;

Jo, Sung-Hyun ;

Lu, Wei .

ACS NANO, 2011, 5 (09) :7669-7676

[5] HfOx/TiOx/HfOx/TiOx Multilayer-Based Forming-Free RRAM Devices With Excellent Uniformity [J].

Fang, Z. ;

Yu, H. Y. ;

Li, X. ;

Singh, N. ;

Lo, G. Q. ;

Kwong, D. L. .

IEEE ELECTRON DEVICE LETTERS, 2011, 32 (04) :566-568

[6]

Govoreanu B, 2011, 2011 IEEE INTERNATIONAL ELECTRON DEVICES MEETING (IEDM)

[7] On the Switching Parameter Variation of Metal-Oxide RRAM-Part I: Physical Modeling and Simulation Methodology [J].

Guan, Ximeng ;

Yu, Shimeng ;

Wong, H. -S. Philip .

IEEE TRANSACTIONS ON ELECTRON DEVICES, 2012, 59 (04) :1172-1182

[8] A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity [J].

Indiveri, G ;

Chicca, E ;

Douglas, R .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (01) :211-221

[9] Nanoscale Memristor Device as Synapse in Neuromorphic Systems [J].

Jo, Sung Hyun ;

Chang, Ting ;

Ebong, Idongesit ;

Bhadviya, Bhavitavya B. ;

Mazumder, Pinaki ;

Lu, Wei .

NANO LETTERS, 2010, 10 (04) :1297-1301

[10]

Kawahara A., 2012, 2012 IEEE International Solid-State Circuits Conference (ISSCC), P432, DOI 10.1109/ISSCC.2012.6177078

← 1 2 3 4 →