Machine learning line bundle connections
Machine learning line bundle connections
复制标题
DOI：
10.1016/j.physletb.2022.136972
复制
发表时间：
2021-10
影响因子：
4.4
通讯作者：
A. Ashmore;R. Deen;Yang-Hui He;B. Ovrut
中科院分区：
文献类型：
--
作者：
A. Ashmore;R. Deen;Yang-Hui He;B. Ovrut
我们研究了利用机器学习来寻找Calabi-Yau流形上的线束上的数值厄米杨-米尔斯连接。我们定义了一个适当的损失函数，并以椭圆曲线、K3曲面和五次三次曲面为例，证明了神经网络可以被训练成近似于厄米杨-米尔斯连接。
We study the use of machine learning for finding numerical hermitian Yang–Mills connections on line bundles over Calabi–Yau manifolds. Defining an appropriate loss function and focusing on the examples of an elliptic curve, a K3 surface and a quintic threefold, we show that neural networks can be trained to give a close approximation to hermitian Yang–Mills connections.