English

SOT-MRAM based Sigmoidal Neuron for Neuromorphic Architectures

Emerging Technologies 2020-06-03 v1 Machine Learning

Abstract

In this paper, the intrinsic physical characteristics of spin-orbit torque (SOT) magnetoresistive random-access memory (MRAM) devices are leveraged to realize sigmoidal neurons in neuromorphic architectures. Performance comparisons with the previous power- and area-efficient sigmoidal neuron circuits exhibit 74x and 12x reduction in power-area-product values for the proposed SOT-MRAM based neuron. To verify the functionally of the proposed neuron within larger scale designs, we have implemented a circuit realization of a 784x16x10 SOT-MRAM based multiplayer perceptron (MLP) for MNIST pattern recognition application using SPICE circuit simulation tool. The results obtained exhibit that the proposed SOT-MRAM based MLP can achieve accuracies comparable to an ideal binarized MLP architecture implemented on GPU, while realizing orders of magnitude increase in processing speed.

Keywords

Cite

@article{arxiv.2006.01238,
  title  = {SOT-MRAM based Sigmoidal Neuron for Neuromorphic Architectures},
  author = {Brendan Reidy and Ramtin Zand},
  journal= {arXiv preprint arXiv:2006.01238},
  year   = {2020}
}
R2 v1 2026-06-23T15:58:32.883Z