We report the use of spin-orbit torque (SOT) magnetoresistive random-access memory (MRAM) to implement a probabilistic binary neural network (PBNN) for resource-saving applications. The in-plane magnetized SOT (i-SOT) MRAM not only enables field-free magnetization switching with high endurance (> 10^11), but also hosts multiple stable probabilistic states with a low device-to-device variation (< 6.35%). Accordingly, the proposed PBNN outperforms other neural networks by achieving an 18* increase in training speed, while maintaining an accuracy above 97% under the write and read noise perturbations. Furthermore, by applying the binarization process with an additional SOT-MRAM dummy module, we demonstrate an on-chip MNIST inference performance close to the ideal baseline using our SOT-PBNN hardware.
@article{arxiv.2309.07789,
title = {SOT-MRAM-Enabled Probabilistic Binary Neural Networks for Noise-Tolerant and Fast Training},
author = {Puyang Huang and Yu Gu and Chenyi Fu and Jiaqi Lu and Yiyao Zhu and Renhe Chen and Yongqi Hu and Yi Ding and Hongchao Zhang and Shiyang Lu and Shouzhong Peng and Weisheng Zhao and Xufeng Kou},
journal= {arXiv preprint arXiv:2309.07789},
year = {2023}
}