Publication Details

Fault Tolerant Field Programmable Neural Networks

KRČMA Martin, KOTÁSEK Zdeněk and KAŠTIL Jan. Fault Tolerant Field Programmable Neural Networks. In: 1st IEEE Nordic Circuits and Systems (NORCAS) Conference. Oslo: IEEE Computer Society, 2015, pp. 1-4. ISBN 978-1-4673-6575-8.
Czech title
FPNN odolná proti poruchám
Type
conference paper
Language
english
Authors
Krčma Martin, Ing. (DCSY FIT BUT)
Kotásek Zdeněk, doc. Ing., CSc. (DCSY FIT BUT)
Kaštil Jan, Ing. (DCSY FIT BUT)
Keywords

FPNA, FPNN, Artificial neural networks, FPGA, Fault Toletant

Abstract

The paper deals with fault tolerant FPNNS. It introduces a method of recovery from faults of one of the unit types without using unit level redundancy based techniques.

Annotation

This paper describes a concept of Field Pro-
grammable Neural Networks (FPNNs) for artificial neural net-
works implementation in FPGAs, presents a model of fault tol-
erant FPNNs and different fault tolerance improving techniques
based on the model. It describes an experiment based on one of
these techniques and presents its results.

Published
2015
Pages
1-4
Proceedings
1st IEEE Nordic Circuits and Systems (NORCAS) Conference
Conference
IEEE Nordic Circuits and Systems Conference, Oslo, NO
ISBN
978-1-4673-6575-8
Publisher
IEEE Computer Society
Place
Oslo, NO
DOI
UT WoS
000380441400028
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11005,
   author = "Martin Kr\v{c}ma and Zden\v{e}k Kot\'{a}sek and Jan Ka\v{s}til",
   title = "Fault Tolerant Field Programmable Neural Networks",
   pages = "1--4",
   booktitle = "1st IEEE Nordic Circuits and Systems (NORCAS) Conference",
   year = 2015,
   location = "Oslo, NO",
   publisher = "IEEE Computer Society",
   ISBN = "978-1-4673-6575-8",
   doi = "10.1109/NORCHIP.2015.7364381",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11005"
}
Back to top