arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.07336math.NAcs.NA
收藏

BelNet:基础增强学习,无网格神经操作器

BelNet: Basis enhanced learning, a mesh-free neural operator

Zecheng Zhang, Wing Tat Leung, Hayden Schaeffer

摘要:

算子学习训练神经网络将函数映射到函数。理想的算子学习框架应该是无网格的,因为训练不需要对输入函数进行特定的离散化选择,允许输入和输出函数在不同的域上,并且能够在样本之间具有不同的网格。提出了一种求解参数型偏微分方程的无网格神经算子。基础增强学习网络(BelNet)将输入函数投影到一个潜在空间中,并重建输出函数。特别是,我们构建的网络的一部分,学习的“基础”的功能,在培训过程中。这推广了Chen和Chen的通用逼近论中提出的网络,用于非线性算子,以考虑输入和输出网格的差异。通过几个具有挑战性的高对比度和多尺度问题,我们证明了我们的方法优于其他算子学习方法,并允许在采样和/或离散化过程中有更多的自由度。

英文摘要:

Operator learning trains a neural network to map functions to functions. An ideal operator learning framework should be mesh-free in the sense that the training does not require a particular choice of discretization for the input functions, allows for the input and output functions to be on different domains, and is able to have different grids between samples. We propose a mesh-free neural operator for solving parametric partial differential equations. The basis enhanced learning network (BelNet) projects the input function into a latent space and reconstructs the output functions. In particular, we construct part of the network to learn the ``basis'' functions in the training process. This generalized the networks proposed in Chen and Chen's universal approximation theory for the nonlinear operators to account for differences in input and output meshes. Through several challenging high-contrast and multiscale problems, we show that our approach outperforms other operator learning methods for these tasks and allows for more freedom in the sampling and/or discretization process.

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。

↑