We study the deformation of the input space by a trained autoencoder via the Jacobians of the trained weight matrices. In doing so, we prove bounds for the mean squared errors for points in the input space, under assumptions regarding the orthogonality of the eigenvectors. We also show that the trace and the product of the eigenvalues of the Jacobian matrices is a good predictor of the MSE on test points. This is a dataset independent means of testing an autoencoder's ability to generalize on new input. Namely, no knowledge of the dataset on which the network was trained is needed, only the parameters of the trained model.
翻译:我们通过经过训练的重量矩阵的Jacobians研究经过训练的自动编码器对输入空间进行变形的问题。 通过这样做,我们证明输入空间各点的平均正方差的界限,这是根据关于源子的正方位的假设进行的。我们还表明,Jacobian矩阵的外形值的痕量和产物是测试点的MSE的良好预测器。这是一个独立的数据集,用来测试自动编码器对新输入进行概括的能力。也就是说,不需要对网络所训练的数据集的了解,而只需要经过训练的模型的参数。