We propose extrinsic and intrinsic deep neural network architectures as general frameworks for deep learning on manifolds. Specifically, extrinsic deep neural networks (eDNNs) preserve geometric features on manifolds by utilizing an equivariant embedding from the manifold to its image in the Euclidean space. Moreover, intrinsic deep neural networks (iDNNs) incorporate the underlying intrinsic geometry of manifolds via exponential and log maps with respect to a Riemannian structure. Consequently, we prove that the empirical risk of the empirical risk minimizers (ERM) of eDNNs and iDNNs converge in optimal rates. Overall, The eDNNs framework is simple and easy to compute, while the iDNNs framework is accurate and fast converging. To demonstrate the utilities of our framework, various simulation studies, and real data analyses are presented with eDNNs and iDNNs.
翻译:我们建议外向和内在深层神经网络结构,作为深入了解方程式的一般框架。具体地说,外向深神经网络(eDNN)利用从方块到其在欧几里德空间的图像的等同嵌入,保留方块上的几何特征。此外,内向深神经网络(iDNN)通过指数图和日志图,结合里曼尼结构,纳入了元件的内在几何特征。因此,我们证明,eDNN和iDNN的实验风险最小化(ERM)的经验风险集中到最佳速率。总体而言,eDNNN框架简单易算,而iDNN框架准确和快速融合。要展示我们框架的效用,各种模拟研究和真实的数据分析都与eDNN和iDNN进行。