The search functionality is under construction.
The search functionality is under construction.

A Low-Cost Training Method of ReRAM Inference Accelerator Chips for Binarized Neural Networks to Recover Accuracy Degradation due to Statistical Variabilities

Zian CHEN, Takashi OHSAWA

  • Full Text Views

    0

  • Cite this

Summary :

A new software based in-situ training (SBIST) method to achieve high accuracies is proposed for binarized neural networks inference accelerator chips in which measured offsets in sense amplifiers (activation binarizers) are transformed into biases in the training software. To expedite this individual training, the initial values for the weights are taken from results of a common forming training process which is conducted in advance by using the offset fluctuation distribution averaged over the fabrication line. SPICE simulation inference results for the accelerator predict that the accuracy recovers to higher than 90% even when the amplifier offset is as large as 40mV only after a few epochs of the individual training.

Publication
IEICE TRANSACTIONS on Electronics Vol.E105-C No.8 pp.375-384
Publication Date
2022/08/01
Publicized
2022/01/31
Online ISSN
1745-1353
DOI
10.1587/transele.2021ECP5040
Type of Manuscript
PAPER
Category
Integrated Electronics

Authors

Zian CHEN
  Waseda University
Takashi OHSAWA
  Waseda University

Keyword