Autoencoder with Ordered Variance for Nonlinear Model Identification
This work addresses model identification for researchers in unsupervised learning, but it appears incremental as it builds on existing autoencoder and ResNet methods.
The paper tackled the problem of extracting nonlinear relationships among input variables in an unsupervised setting by introducing an autoencoder with ordered variance (AEO) and its ResNet variant (RAEO), which enforce order in the latent space through a modified loss function with variance regularization.
This paper presents a novel autoencoder with ordered variance (AEO) in which the loss function is modified with a variance regularization term to enforce order in the latent space. Further, the autoencoder is modified using ResNets, which results in a ResNet AEO (RAEO). The paper also illustrates the effectiveness of AEO and RAEO in extracting nonlinear relationships among input variables in an unsupervised setting.