Robustness against SEU of an artificial neural network space application

被引：8

作者：

Assoum, A

Radi, NE

Velazco, R

Elie, F

Ecoffet, R

机构：

[1] CNRS,LPCE,F-45071 ORLEANS,FRANCE

[2] CTR NATL ETUD SPATIALES,F-31055 TOULOUSE,FRANCE

来源：

IEEE TRANSACTIONS ON NUCLEAR SCIENCE | 1996年 / 43卷 / 03期

关键词：

D O I：

10.1109/23.510742

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：

We study the sensitivity of Artificial Neural Networks (ANN) to Single Event Upsets (SEU). A neural network designed to detect electronic and protonic whistlers has been implemented using a dedicated VLSI circuit: the LNeuro neural processor. Results of both SEU software simulations and heavy ion tests point out the fault tolerance properties of ANN hardware implementations.

引用

页码：973 / 978

页数：6

共 14 条

[1]

Angeniol B., 1990, Neural Networks: Biological Computers or Electronic Brains, P65

[2]

KERLIRZIN P, 1993, NEURAL COMPUT, P473

[3] WEIGHT SHIFTING TECHNIQUES FOR SELF-RECOVERY NEURAL NETWORKS [J].

KHUNASARAPHAN, C ;

VANAPIPAT, K ;

LURSINSAP, C .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (04) :651-658

[4] LNEURO 1.0 - A PIECE OF HARDWARE LEGO FOR BUILDING NEURAL NETWORK SYSTEMS [J].

MAUDUIT, N ;

DURANTON, M ;

GOBERT, J ;

SIRAT, JA .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (03) :414-422

[5]

MINIERE X, IN PRESS J ATMOSPHER

[6] ENHANCED MLP PERFORMANCE AND FAULT-TOLERANCE RESULTING FROM SYNAPTIC WEIGHT NOISE DURING TRAINING [J].

MURRAY, AF ;

EDWARDS, PJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (05) :792-802

[7]

Rumelhart D. E., 1986, PARALLEL DISTRIBUTED, V1

[8]

SANCHEZSINENCIO E, 1993, IEEE T NEURAL NETWOR, V4, P385

[9]

SANCHEZSINENCIO E, 1993, IEEE T NEURAL NETWOR, V4, P387

[10]

SEQUIN CH, 1990, IJCNN INT JOINT C NE, V1, P703

← 1 2 →