Abstract
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 (RNN). 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 RNN, such optimization is not necessary for RC. The reservoir only has to possess a nonlinear response with memory effect. In this paper, macromagnetic simulation is conducted for the spin dynamics in MTJs for RC. It is determined that the MTJ system possesses the memory effect and nonlinearity 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.
1 More- Received 25 May 2018
- Revised 21 August 2018
DOI:https://doi.org/10.1103/PhysRevApplied.10.034063
© 2018 American Physical Society