arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.03804cond-mat.str-elcond-mat.dis-nncond-mat.mtrl-scics.LG
收藏

用于巡游磁体自旋动力学模拟的等变神经网络

Equivariant Neural Networks for Spin Dynamics Simulations of Itinerant Magnets

The University of Tokyo(东京大学)

Yu Miyazaki

AI总结:

提出等变神经网络用于Kondo晶格模型自旋动力学模拟,确保平移与旋转等变性,显著降低验证误差,并成功再现斯格明子晶体相变。

摘要:

我提出了一种新颖的等变神经网络架构,用于Kondo晶格模型的大规模自旋动力学模拟。该神经网络主要由基于张量积的卷积层组成,并确保两种等变性:晶格的平移和自旋的旋转。我在二维正方形和三角形晶格上实现了两种Kondo晶格模型的等变神经网络,并进行了训练和验证。在正方形晶格的等变模型中,验证误差(基于均方根误差)相较于使用不变描述符作为输入的模型降低至不足三分之一。此外,我通过使用训练后的模型进行动力学模拟,展示了在三角形晶格中再现斯格明子晶体相变的能力。

英文摘要:

I present a novel equivariant neural network architecture for the large-scale spin dynamics simulation of the Kondo lattice model. This neural network mainly consists of tensor-product-based convolution layers and ensures two equivariances: translations of the lattice and rotations of the spins. I implement equivariant neural networks for two Kondo lattice models on two-dimensional square and triangular lattices, and perform training and validation. In the equivariant model for the square lattice, the validation error (based on root mean squared error) is reduced to less than one-third compared to a model using invariant descriptors as inputs. Furthermore, I demonstrate the ability to reproduce phase transitions of skyrmion crystals in the triangular lattice, by performing dynamics simulations using the trained model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑