Robustness evaluation of restricted Boltzmann machine against memory and logic error

Yasushi Fukuda, Zule Xu, Takayuki Kawahara

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In an IoT system, neural networks have the potential to perform advanced information processing in various environments. To clarify this, the robustness of a restricted Boltzmann machine (RBM) used for deep neural networks, such as a deep belief network (DBN), was studied in this paper. Even if memory or logic errors occurred in the circuit operating in the RBM while pre-training the DBN, they did not affect the identification rate of the DBN, showing the robustness of the RBM. In addition, robustness against soft errors was evaluated. The soft errors had almost no influence on the RBM unless they were as large as 1012 times or more in the 50-nm CMOS process.

Original languageEnglish
Pages (from-to)1118-1121
Number of pages4
JournalIEICE Transactions on Electronics
VolumeE100C
Issue number12
DOIs
Publication statusPublished - 1 Dec 2017

Keywords

  • DBN
  • IoT
  • Neural network
  • RBM
  • Soft error

Cite this