Open AccessActivation function and computing performance of spin neuron driven by magnetic field and strain
Author(s) -
Jiahui Yuan,
Xiaokuo Yang,
Bin Zhang,
Ya-Bo Chen,
Jun Zhong,
Bo Wei,
Mingxu Song,
Huanqing Cui
Publication year - 2021
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.70.20210611
Subject(s) - mnist database , artificial neuron , artificial neural network , activation function , computer science , neuron , micromagnetics , field (mathematics) , magnetic field , cmos , magnetization , condensed matter physics , artificial intelligence , topology (electrical circuits) , physics , electrical engineering , optoelectronics , mathematics , neuroscience , quantum mechanics , engineering , pure mathematics , biology
The spin neuron is an emerging artificial neural device which has many advantages such as ultra-low power consumption, strong nonlinearity, and high integration. Besides, it has ability to remember and calculate at the same time. So it is seen as a suitable and excellent candidate for the new generation of neural network. In this paper, a spin neuron driven by magnetic field and strain is proposed. The micromagnetic model of the device is realized by using the OOMMF micromagnetic simulation software, and the numerical model of the device is also established by using the LLG equation. More importantly, a three-layer neural network is composed of spin neurons constructed respectively using three materials (Terfenol-D, FeGa, Ni). It is used to study the activation functions and the ability to recognize the MNIST handwritten datasets.c Results show that the spin neuron can successfully achieve the random magnetization switching to simulate the activation behavior of the biological neuron. Moreover, the results show that if the ranges of the inputting magnetic fields are different, the three materials' neurons can all reach the saturation accuracy. It is expected to replace the traditional CMOS neuron. And the overall power consumption of intelligent computing can be further reduced by using appropriate materials. If we input the magnetic fields in the same range, the recognition speed of the spin neuron made of Ni is the slowest in the three materials. The results can establish a theoretical foundation for the design and the applications of the new artificial neural networks and the intelligent circuits.