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

研究成果: Article査読

抄録

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.

本文言語English
ページ(範囲)375-384
ページ数10
ジャーナルIEICE Transactions on Electronics
E105.C
8
DOI
出版ステータスPublished - 2022 8月

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 電子工学および電気工学

フィンガープリント

「A Low-Cost Training Method of ReRAM Inference Accelerator Chips for Binarized Neural Networks to Recover Accuracy Degradation due to Statistical Variabilities」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル