The Impact of Proton-Induced Single Events on Image Classification in a Neuromorphic Computing Architecture

被引：14

作者：

Brewer, Rachel M. ^{[1
]}

Reed, Robert A. ^{[1
]}

Moran, Steven L. ^{[2
]}

Cox, Jonathan ^{[2
]}

Sierawski, Brian D. ^{[1
]}

McCurdy, Michael W. ^{[1
]}

Zhang, En Xia ^{[1
]}

Iyer, Subramanian S. ^{[2
]}

Schrimpf, Ronald D. ^{[1
]}

Alles, Michael L. ^{[1
]}

机构：

[1] Vanderbilt Univ, Dept Elect Engn & Comp Sci, 221 Kirkland Hall, Nashville, TN 37235 USA

[2] Univ Calif Los Angeles, Dept Elect Engn, Los Angeles, CA 90095 USA

来源：

IEEE TRANSACTIONS ON NUCLEAR SCIENCE | 2020年 / 67卷 / 01期

关键词：

Classification changes; modified national institute of standards and technology (MNIST); neuromorphic computing; proton irradiation; single-event effects (SEEs); single-event upsets (SEUs); TrueNorth neurosynaptic system; NETWORK; DESIGN;

D O I：

10.1109/TNS.2019.2957477

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Neuromorphic computing endeavors to imitate the way biological brains process information and solve problems. Uses for neuromorphic computing span disciplines and include applications in image processing, audio processing, optimization, and more. This work explores the effect of proton-induced single-event upsets (SEUs) on a neuromorphic computing architecture engaged in image recognition. Two main results are found. One, the overall classification accuracy is unchanged although a high number of hidden, tolerable errors occurred. Additionally, SEUs are found to alter the relative occurrence of false positives and false negatives, which occurred despite the overall classification accuracy remaining unaffected.

引用

页码：108 / 115

页数：8

共 16 条

[1] True North: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip
Akopyan, Filipp
Sawada, Jun
Cassidy, Andrew
Alvarez-Icaza, Rodrigo
Arthur, John
Merolla, Paul
Imam, Nabil
Nakamura, Yutaka
Datta, Pallab
Nam, Gi-Joon
Taba, Brian
Beakes, Michael
Brezzo, Bernard
Kuang, Jente B.
Manohar, Rajit
Risk, William P.
Jackson, Bryan
Modha, Dharmendra S.
[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2015, 34 (10) : 1537 - 1557
[2] [Anonymous], [No title captured]
[3] [Anonymous], [No title captured]
[4] Artificial neural networks: fundamentals, computing, design, and application
Basheer, IA
Hajmeer, M
[J]. JOURNAL OF MICROBIOLOGICAL METHODS, 2000, 43 (01) : 3 - 31
[5] Pulsed laser validation of recovery mechanisms of critical SEE's in an artificial neural network system.
Buchner, S
Olmos, M
Cheynet, P
Velazco, R
McMorrow, D
Melinger, J
Ecoffet, R
Muller, JD
[J]. IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 1998, 45 (03) : 1501 - 1507
[6] Training invariant support vector machines
Decoste, D
Schölkopf, B
[J]. MACHINE LEARNING, 2002, 46 (1-3) : 161 - 190
[7] Analyzing and Increasing the Reliability of Convolutional Neural Networks on GPUs
dos Santos, Fernando Fernandes
Pimenta, Pedro Foletto
Lunardi, Caio
Draghetti, Lucas
Carro, Luigi
Kaeli, David
Rech, Paolo
[J]. IEEE TRANSACTIONS ON RELIABILITY, 2019, 68 (02) : 663 - 677
[8] Gradient-based learning applied to document recognition
Lecun, Y
Bottou, L
Bengio, Y
Haffner, P
[J]. PROCEEDINGS OF THE IEEE, 1998, 86 (11) : 2278 - 2324
[9] Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications
Li, Guanpeng
Hari, Siva Kumar Sastry
Sullivan, Michael
Tsai, Timothy
Pattabiraman, Karthik
Emer, Joel
Keckler, Stephen W.
[J]. SC'17: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, 2017,
[10] Selective Hardening for Neural Networks in FPGAs
Libano, F.
Wilson, B.
Anderson, J.
Wirthlin, M. J.
Cazzaniga, C.
Frost, C.
Rech, P.
[J]. IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2019, 66 (01) : 216 - 222

← 1 2 →