English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

I present a novel equivariant neural network architecture for the large-scalespin dynamics simulation of the Kondo lattice model. This neural network mainlyconsists of tensor-product-based convolution layers and ensures twoequivariances: translations of the lattice and rotations of the spins. Iimplement equivariant neural networks for two Kondo lattice models ontwo-dimensional square and triangular lattices, and perform training andvalidation. In the equivariant model for the square lattice, the validationerror (based on root mean squared error) is reduced to less than one-thirdcompared to a model using invariant descriptors as inputs. Furthermore, Idemonstrate the ability to reproduce phase transitions of skyrmion crystals inthe triangular lattice, by performing dynamics simulations using the trainedmodel.

Equivariant Neural Networks for Spin Dynamics Simulations of Itinerant Magnets