… transforming auto-encoder direct knowledge of the transformation, we can model the small
transformations … This reduces the transforming auto-encoder to a much less powerful learning …

… They extend auto-encoders with an equivariant latent code, … its equivariance wrt example
transformations. A single capsule … Transforming auto-encoders. In International conference on …

We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which
integrates discriminative and generative pathways and provides a unified approach to …

… auto-encoders from three different perspectives. We also discuss the relationships between
auto-encoders, … Then, we focus on the available toolkits for auto-encoders. Finally, this paper …

… Variational auto-encoders (VAE) are scalable and powerful … , ie, a series of invertible
transformations to latent variables with a … transformations that we refer to as the Householder flow. …

… to transform images, we seek to train auto-encoders that … transformed images. We believe
as long as the trained features are sufficiently informative, we can decode the transformations …

… GANs can be treated as a special type of auto-encoders, and various auto-encoders are
widely used for computer vision tasks, such as face images [10], [11], animations [12] and …

… transformations in deep networks, purely from data, without being given a model of those
transformations. … equivariant to image translation, a transformation that can be easily modelled (…

… Have one stack of auto-encoders for each modality, used to transform each modalities data
X(t) into a representation where the marginal P(X(t)) can be captured easily through some P(…

… utilizes deterministic and discrete transformations of data. This … transformation as a latent
variable, where the transformation … architecture, ie, multiple transformations, and we show its …