Publication detail

Triple Modular Redundancy Used in Field Programmable Neural Networks

KRČMA, M. LOJDA, J. KOTÁSEK, Z.

Original Title

Triple Modular Redundancy Used in Field Programmable Neural Networks

Type

conference paper

Language

English

Original Abstract

This paper presents the concepts of FPNA and FPNN, used for the approximation of artificial neural networks in FPGAs and discusses the usage of TMR technique in order to reach a fault tolerance. The schemes of the FPGA implementation are presented. The results of experiments determining the FPGA resources utilization with different usage of the TMR technique are provided.

Keywords

Tripple Modular Redundancy, FPNN, Aritificial Neural networks, Fault Tolerance

Authors

KRČMA, M.; LOJDA, J.; KOTÁSEK, Z.

Released

29. 9. 2017

Publisher

IEEE Computer Society

Location

Novi Sad

ISBN

978-1-5386-3299-4

Book

Proceedings of IEEE East-West Design & Test Symposium

Pages from

1

Pages to

6

Pages count

6

URL

https://www.fit.vut.cz/research/publication/11446/

BibTex

@inproceedings{BUT146262,
  author="Martin {Krčma} and Jakub {Lojda} and Zdeněk {Kotásek}",
  title="Triple Modular Redundancy Used in Field Programmable Neural Networks",
  booktitle="Proceedings of IEEE East-West Design & Test Symposium",
  year="2017",
  pages="1--6",
  publisher="IEEE Computer Society",
  address="Novi Sad",
  doi="10.1109/EWDTS.2017.8110128",
  isbn="978-1-5386-3299-4",
  url="https://www.fit.vut.cz/research/publication/11446/"
}