no code implementations • 5 Jul 2023 • Sosei Ikeda, Hiromitsu Awano, Takashi Sato
However, digital DFRs emulate analog nonlinear components in the digital domain, resulting in a lack of design flexibility and higher power consumption.
no code implementations • 25 Jan 2022 • Kyohei Shimozato, Michihiro Shintani, Takashi Sato
Outlier detection of semiconductor devices is important since manufacturing variation is inherently inevitable.
no code implementations • 22 Oct 2021 • Michihiro Shintani, Aoi Ueda, Takashi Sato
The extraction of the model parameters is as important as the development of compact model itself because simulation accuracy is fully determined by the accuracy of the parameters used.
1 code implementation • 19 Oct 2020 • Kotaro Matsuoka, Ryotaro Banno, Naoki Matsumoto, Takashi Sato, Song Bian
Our experiments show that both the pipelined architecture and the CMUX Memory technique are effective in improving the performance of the proposed processor.
Cryptography and Security
no code implementations • 11 Aug 2020 • Kenta Nagura, Song Bian, Takashi Sato
In this work, we find out that averaging models from different clients significantly diminishes the norm of the update vectors, resulting in slow learning rate and low prediction accuracy.
no code implementations • 14 Jul 2020 • Song Bian, Xiaowei Xu, Weiwen Jiang, Yiyu Shi, Takashi Sato
The strict security requirements placed on medical records by various privacy regulations become major obstacles in the age of big data.
no code implementations • CVPR 2020 • Song Bian, Tianchen Wang, Masayuki Hiromoto, Yiyu Shi, Takashi Sato
In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacy-preserving visual recognition.
no code implementations • 30 Jan 2020 • Song Bian, Weiwen Jiang, Qing Lu, Yiyu Shi, Takashi Sato
Due to increasing privacy concerns, neural network (NN) based secure inference (SI) schemes that simultaneously hide the client inputs and server models attract major research interests.