Detail publikace

Detecting hard synapses faults in artificial neural networks

KRČMA, M. KOTÁSEK, Z. LOJDA, J.

Originální název

Detecting hard synapses faults in artificial neural networks

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper presents the concepts of detecting hard faults in artificial neural network synapses using the modification of the neural network settings. The core of this work is based on weights values modification and inserting the chosen testing data when comparing the neural network output to the known valid results. The paper also discuss the problem of neural network output saturation and provide experiments on influence of the neural network settings to the problem in this regard.

Klíčová slova

artificial neural networks, hard faults, faults detection, fault tolerance

Autoři

KRČMA, M.; KOTÁSEK, Z.; LOJDA, J.

Vydáno

11. 3. 2019

Nakladatel

IEEE Computer Society

Místo

Santiago de Chile

ISBN

978-1-7281-1756-0

Kniha

20th IEEE Latin American Test Symposium (LATS 2019)

Strany od

1

Strany do

6

Strany počet

6

URL

https://www.fit.vut.cz/research/publication/11876/

BibTex

@inproceedings{BUT159964,
  author="Martin {Krčma} and Zdeněk {Kotásek} and Jakub {Lojda}",
  title="Detecting hard synapses faults in artificial neural networks",
  booktitle="20th IEEE Latin American Test Symposium (LATS 2019)",
  year="2019",
  pages="1--6",
  publisher="IEEE Computer Society",
  address="Santiago de Chile",
  doi="10.1109/LATW.2019.8704637",
  isbn="978-1-7281-1756-0",
  url="https://www.fit.vut.cz/research/publication/11876/"
}