Unsupervised Representation Learning from Sparse Transformation Analysis

Understand

There is a vast literature on representation learning based on principles such as coding efficiency, statistical independence, causality, controllability, or symmetry.

• In this paper we propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components.
• Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model, before being decoded to predict a future input state.
• The flow model is decomposed into a number of rotational (divergence-free) vector fields and a number of potential flow (curl-free) fields.