Reservoir computing by a thin film embedded with magnetic impurities

Reservoir computing based on a thin film embedded with magnetic impurities in the presence of a long-range (the dipole–dipole) interaction is numerically investigated. We simulated the magnetization dynamics by taking into account the dipole–dipole interaction and performed a handwritten-digit recognition task. Although the training data is prepared by taking the spatial average in the sample, high classification accuracy is achieved. Our result demonstrates that the long-range interaction effectively encodes the complex spatial input pattern into the time domain, even when only a spatially averaged output is accessible. The proposed system paves the way for easily realizable magnetic reservoir computing.