Reservoir computing with dipole-coupled nanomagnets

Abstract

The feasibility of reservoir computing based on dipole-coupled nanomagnets is demonstrated using micro-magnetic simulations at 0 K. The static-magnetization directions of the nanomagnets are used as reservoir states. To update these states, we change the magnetization of one nanomagnet according to a single-bit-sequential input signal. We also change the uniaxial-anisotropy of the other nanomagnets using a voltage-induced magnetic anisotropy change to facilitate the flow of information, storage, and linear/nonlinear calculations. As a result, the reservoir computing output matrix was found to be trainable to perform AND/OR/XOR operations with an input delay of up to three bits.