The lack of crisp mathematical models that capture the structure of real-world data sets is a major obstacle to the detailed theoretical understanding of deep neural networks. Here, we first demonstrate the effect of structured data sets by experimentally comparing the dynamics and the performance of two-layer networks trained on two different data sets: (i) an unstructured synthetic data set containing random i.i.d. inputs, and (ii) a simple canonical data set containing MNIST images. Our analysis reveals two phenomena related to the dynamics of the networks and their ability to generalise that only appear when training on structured data sets. Second, we introduce a generative model for data sets, where high-dimensional inputs lie on a lower-dimensional manifold and have labels that depend only on their position within this manifold. We call it the hidden manifold model and we experimentally demonstrate that training networks on data sets drawn from this model reproduces both the phenomena seen during training on MNIST.

本文提出了一个名为“隐藏流形模型”的生成模型，证明了随机梯度下降算法训练的两层神经网络表现的动态可以通过Integro-differential方程组进行跟踪，同时分析了神经网络训练过程中神经网络学习增加复杂度和提高性能的方式以及受其大小、学习率和隐藏流形维度等参数的影响。

神经网络中数据结构对学习的影响建模：隐藏流形模型