Published June 1996 | Version v1
Journal article

Robustness against S.E.U. of an artificial neural network space application

  • 1. IMAG, Grenoble (France). Lab. de Genie Informatique
  • 2. CNRS, Orleans (France). Lab. de Physique et Chimie d l'Environnement
  • 3. Centre National d'Etudes Spatiales, Toulouse (France)

Description

The authors 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

Additional details

Publishing Information

Journal Title
IEEE Transactions on Nuclear Science
Journal Volume
43
Journal Issue
3Pt1
Journal Page Range
p. 973-978.
ISSN
0018-9499
CODEN
IETNAE

Conference

Title
3. European symposium on radiations and their effects on components and systems.
Dates
18-22 Sep 1995.
Place
Arcachon (France).

INIS

Country of Publication
United States
Country of Input or Organization
United States
INIS RN
27075943
Subject category
S46: INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY;
Resource subtype / Literary indicator
Conference, Numerical Data
Descriptors DEI
COMPUTERIZED SIMULATION; ERRORS; EXPERIMENTAL DATA; INTEGRATED CIRCUITS; IONIZING RADIATIONS; NEURAL NETWORKS; PHYSICAL RADIATION EFFECTS; SPACE FLIGHT; THEORETICAL DATA
Descriptors DEC
DATA; ELECTRONIC CIRCUITS; INFORMATION; NUMERICAL DATA; RADIATION EFFECTS; RADIATIONS; SIMULATION

Optional Information

Secondary number(s)
CONF-9509107--.