Spintronic virtual neural network by a voltage controlled ferromagnet for associative memory

Abstract

Recently, an associative memory operation by a virtual oscillator network, consisting of a single spintronic oscillator, was examined to solve issues in conventional, real oscillators-based neural networks such as inhomogeneities between the oscillators. However, the spintronic oscillator still carries issues dissipating large amount of energy because it is driven by electric current. Here, we propose to use a single ferromagnet manipulated by voltage-controlled magnetic anisotropy (VCMA) effect as a fundamental element in a virtual neural network, which will contribute to significantly reducing the Joule heating caused by electric current. Instead of the oscillation in oscillator networks, magnetization relaxation dynamics were used for the associative memory operation. The associative memory operation for alphabet patterns is successfully demonstrated by giving correspondences between the colors in a pattern recognition task and the sign of a perpendicular magnetic anisotropy coefficient, which could be either positive or negative via the VCMA effect.

Sparse reservoir computing with vertically coupled vortex spin-torque oscillators for time series prediction

“…A multi-layer spintronic neural network architecture utilizing magnetic tunnel junctions was introduced to directly process radio frequency input signals [12]. Furthermore, a virtual neural network system based on a single ferromagnetic body proved effective for associative memory operations involving letter patterns [13]. A particular advantage of spintronic devices is that its magnetic dynamics can be well represented by the magnetoresistance effect and manipulated by the magnetic field, spin transfer torque (STT) or spin-orbit torque [14][15][16].…”