In deploying the Internet of Things (IoT) and Internet of Medical Things (IoMT)-based applications and infrastructures, the researchers faced many sensors and their output's …
Z Chen, T Ohsawa - IEICE Transactions on Electronics, 2022 - search.ieice.org
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 …
Y Mei, T Ohsawa - IEICE Transactions on Electronics, 2023 - search.ieice.org
A fully analog pipelined deep neural network (DNN) accelerator is proposed, which is constructed by using pipeline registers based on master-slave switched capacitors. The idea …
S Gao, T Ohsawa - Japanese Journal of Applied Physics, 2024 - iopscience.iop.org
We propose a novel training method named hardware-conscious software training (HCST) for deep neural network inference accelerators to recover the accuracy degradation due to …