The figures-of-merit for reservoir computing (RC), using spintronics devices called magnetic tunnel junctions (MTJs), are evaluated. RC is a type of recurrent neural network. The input information is stored in certain parts of the reservoir, and computation can be performed by optimizing a linear transform matrix for the output. While all the network characteristics should be controlled in a general recurrent neural network, such optimization is not necessary for RC. The reservoir only has to possess a non-linear response with memory effect. In this paper, macromagnetic simulation is conducted for the spin-dynamics in MTJs, for reservoir computing. It is determined that the MTJ-system possesses the memory effect and non-linearity required for RC. With RC using 5-7 MTJs, high performance can be obtained, similar to an echo-state network with 20-30 nodes, even if there are no magnetic and/or electrical interactions between the magnetizations.
@article{arxiv.1805.09977,
title = {Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions},
author = {Taishi Furuta and Keisuke Fujii and Kohei Nakajima and Sumito Tsunegi and Hitoshi Kubota and Yoshishige Suzuki and Shinji Miwa},
journal= {arXiv preprint arXiv:1805.09977},
year = {2018}
}