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 1905.02789math.NAcs.LGcs.NAstat.ML
收藏

物理模型解映射的神经网络近似的变分训练

Variational training of neural network approximations of solution maps for physical models

Duke University(杜克大学);Shanghai Jiao Tong University(上海交通大学)

Yingzhou Li, Jianfeng Lu, Anqi Mao

摘要:

提出了一种新的求解-训练框架,用于训练神经网络表示物理模型的低维解映射。求解-训练框架使用神经网络作为解映射的模拟器,并通过来自底层物理模型的损失函数变化地训练网络。求解训练框架避免了传统监督训练过程中为输入数据准备标签的昂贵数据准备,并且仍然实现了适应输入数据分布的解决方案映射的有效表示。通过获得线性和非线性椭圆方程的解映射以及线性和非线性薛定谔方程的势到基态的映射,证明了求解训练框架的有效性.

英文摘要:

A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural network as the ansatz of the solution map and train the network variationally via loss functions from the underlying physical models. Solve-training framework avoids expensive data preparation in the traditional supervised training procedure, which prepares labels for input data, and still achieves effective representation of the solution map adapted to the input data distribution. The efficiency of solve-training framework is demonstrated through obtaining solutions maps for linear and nonlinear elliptic equations, and maps from potentials to ground states of linear and nonlinear Schrödinger equations.

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。

↑