FeFET-based Binarized Neural Networks Under Temperature-dependent Bit Errors

Mikail Yayla, Sebastian Buschjager, Aniket Gupta, Jian Jia Chen, Jorg Henkel, Katharina Morik, Kuan Hsun Chen, Hussam Amrouch

Research output: Contribution to journalArticleAcademicpeer-review

10 Citations (Scopus)
31 Downloads (Pure)


Ferroelectric FET (FeFET) is a highly promising emerging non-volatile memory (NVM) technology, especially for binarized neural network (BNN) inference on the low-power edge. The reliability of such devices, however, inherently depends on temperature. Hence, changes in temperature during run time manifest themselves as changes in bit error rates. In this work, we reveal the temperature-dependent bit error model of FeFET memories, evaluate its effect on BNN accuracy, and propose countermeasures. We begin on the transistor level and accurately model the impact of temperature on bit error rates of FeFET. This analysis reveals temperature-dependent asymmetric bit error rates. Afterwards, on the application level, we evaluate the impact of the temperature-dependent bit errors on the accuracy of BNNs. Under such bit errors, the BNN accuracy drops to unacceptable levels when no countermeasures are employed. We propose two countermeasures: (1) Training BNNs for bit error tolerance by injecting bit flips into the BNN data, and (2) applying a bit error rate assignment algorithm (BERA) which operates in a layer-wise manner and does not inject bit flips during training. In experiments, the BNNs, to which the countermeasures are applied to, effectively tolerate temperature-dependent bit errors for the entire range of operating temperature.

Original languageEnglish
Pages (from-to)1681-1695
Number of pages1
JournalIEEE transactions on computers
Issue number7
Early online date13 Aug 2021
Publication statusPublished - 1 Jul 2022
Externally publishedYes


  • Artificial neural networks
  • Bit error rate
  • bit error tolerance
  • FeFET
  • FeFETs
  • neural networks
  • Non-volatile memory
  • Nonvolatile memory
  • Random access memory
  • Solid modeling
  • temperature
  • Voltage measurement


Dive into the research topics of 'FeFET-based Binarized Neural Networks Under Temperature-dependent Bit Errors'. Together they form a unique fingerprint.

Cite this