arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.09940cs.LGcs.NAmath.NA
收藏

基于Grassmann层的浅ReLU网络降阶建模

Reduced Order Modeling using Shallow ReLU Networks with Grassmann Layers

Carnegie Mellon University(卡内基梅隆大学)

Kayla Bollinger, Hayden Schaeffer

摘要:

本文提出了一种利用结构化神经网络对方程组进行非线性模型降阶的方法。神经网络采用“三层”网络的形式,第一层被约束为位于格拉斯曼流形上,第一个激活函数被设置为恒等式,而剩余的网络是标准的两层ReLU神经网络。格拉斯曼层确定输入空间的简化基,而其余层近似非线性输入-输出系统。训练在学习缩减基和非线性近似之间交替进行,并且被证明比固定缩减基和仅训练网络更有效。这种方法的另一个好处是,对于位于低维子空间上的数据,网络中的参数数量不需要很大。我们表明,我们的方法可以应用于科学问题的数据稀缺制度,这是典型的不太适合神经网络近似。例子包括非线性动态系统和几个航空航天工程问题的降阶建模。

英文摘要:

This paper presents a nonlinear model reduction method for systems of equations using a structured neural network. The neural network takes the form of a "three-layer" network with the first layer constrained to lie on the Grassmann manifold and the first activation function set to identity, while the remaining network is a standard two-layer ReLU neural network. The Grassmann layer determines the reduced basis for the input space, while the remaining layers approximate the nonlinear input-output system. The training alternates between learning the reduced basis and the nonlinear approximation, and is shown to be more effective than fixing the reduced basis and training the network only. An additional benefit of this approach is, for data that lie on low-dimensional subspaces, that the number of parameters in the network does not need to be large. We show that our method can be applied to scientific problems in the data-scarce regime, which is typically not well-suited for neural network approximations. Examples include reduced order modeling for nonlinear dynamical systems and several aerospace engineering problems.

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。

↑