Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/112281
Title: Recurrent Network Classifier for Ultrafast Skyrmion Dynamics
Authors: Deviatov, A. Y.
Iakovlev, I. A.
Mazurenko, V. V.
Issue Date: 2019
Publisher: American Physical Society
American Physical Society (APS)
Citation: Deviatov A. Y. Recurrent Network Classifier for Ultrafast Skyrmion Dynamics / A. Y. Deviatov, I. A. Iakovlev, V. V. Mazurenko // Physical Review Applied. — 2019. — Vol. 12. — Iss. 5. — 054026.
Abstract: 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. © 2019 American Physical Society.
Keywords: DYNAMICS
MAGNETIZATION
NANOSYSTEMS
VIRTUAL STORAGE
AUTONOMOUS CONTROL SYSTEMS
DATA STORAGE DEVICES
DZYALOSHINSKII-MORIYA INTERACTION
FINITE TEMPERATURES
MAGNETIZATION VECTOR
RECURRENT NETWORKS
ULTRAFAST MAGNETIZATION
ZERO TEMPERATURES
RECURRENT NEURAL NETWORKS
URI: http://hdl.handle.net/10995/112281
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85075134202
PURE ID: 11347646
ISSN: 2331-7019
metadata.dc.description.sponsorship: We thank Yaroslav Kvashnin and Anders Bergman for fruitful discussions and technical assistance with the uppasd package. This work is supported by the Russian Science Foundation Grant No. 18-12-00185.
RSCF project card: 18-12-00185
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85075134202.pdf3,18 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.