以模型为中心的数据流形:模型眼中的数据
Model-centric Data Manifold: the Data Through the Eyes of the Model
摘要:
我们发现,深度ReLU神经网络分类器可以在数据上看到低维黎曼流形结构。这种结构通过局部数据矩阵来实现,局部数据矩阵是Fisher信息矩阵的变体,其中模型参数的作用由数据变量承担。我们获得了数据域的叶,我们表明,模型训练的数据集位于一个叶子上,数据叶子,其维度由分类标签的数量限制。我们用MNIST数据集的一些实验来验证我们的结果:数据叶上的路径连接有效图像,而其他叶子覆盖噪声图像。
英文摘要:
We discover that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold structure on data. Such structure comes via the local data matrix, a variation of the Fisher information matrix, where the role of the model parameters is taken by the data variables. We obtain a foliation of the data domain and we show that the dataset on which the model is trained lies on a leaf, the data leaf, whose dimension is bounded by the number of classification labels. We validate our results with some experiments with the MNIST dataset: paths on the data leaf connect valid images, while other leaves cover noisy images.
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。