English

Hardware-aware $in \ situ$ Boltzmann machine learning using stochastic magnetic tunnel junctions

Mesoscale and Nanoscale Physics 2022-01-17 v2 Disordered Systems and Neural Networks Emerging Technologies

Abstract

One of the big challenges of current electronics is the design and implementation of hardware neural networks that perform fast and energy-efficient machine learning. Spintronics is a promising catalyst for this field with the capabilities of nanosecond operation and compatibility with existing microelectronics. Considering large-scale, viable neuromorphic systems however, variability of device properties is a serious concern. In this paper, we show an autonomously operating circuit that performs hardware-aware machine learning utilizing probabilistic neurons built with stochastic magnetic tunnel junctions. We show that in situin \ situ learning of weights and biases in a Boltzmann machine can counter device-to-device variations and learn the probability distribution of meaningful operations such as a full adder. This scalable autonomously operating learning circuit using spintronics-based neurons could be especially of interest for standalone artificial-intelligence devices capable of fast and efficient learning at the edge.

Keywords

Cite

@article{arxiv.2102.05137,
  title  = {Hardware-aware $in \ situ$ Boltzmann machine learning using stochastic magnetic tunnel junctions},
  author = {Jan Kaiser and William A. Borders and Kerem Y. Camsari and Shunsuke Fukami and Hideo Ohno and Supriyo Datta},
  journal= {arXiv preprint arXiv:2102.05137},
  year   = {2022}
}
R2 v1 2026-06-23T22:59:58.852Z