Publication detail

Detecting hard synapses faults in artificial neural networks

KRČMA, M. KOTÁSEK, Z. LOJDA, J.

Original Title

Detecting hard synapses faults in artificial neural networks

Type

conference paper

Language

English

Original Abstract

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.

Keywords

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

Authors

KRČMA, M.; KOTÁSEK, Z.; LOJDA, J.

Released

11. 3. 2019

Publisher

IEEE Computer Society

Location

Santiago de Chile

ISBN

978-1-7281-1756-0

Book

20th IEEE Latin American Test Symposium (LATS 2019)

Pages from

1

Pages to

6

Pages count

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/"
}