Recurrent Network Classifier for Ultrafast Skyrmion Dynamics

By using supervised learning, we train a recurrent neural network to recognize and classify ultrafast magnetization processes that are realized in two-dimensional nanosystems with Dzyaloshinskii-Moriya interactions. Our focus is on different types of skyrmion dynamics driven by ultrafast magnetic pulses. Each process is represented as a sequence of sorted magnetization vectors that are inputted into the network. The trained network can perform an accurate classification of the skyrmionic processes at zero temperature over a wide range of magnetic pulse widths and damping factors. The network performance is also demonstrated on different types of unseen data, including finite-temperature processes. Our approach can be easily adapted for creating an autonomous control system on skyrmion dynamics for experiments or data-storage devices.