A disentangled recognition and nonlinear dynamics model for Unsupervised Learning

Dive into the conversation around unsupervised learning and its impact within Raffle to understand our unique structure.
Marco Fraccaro, Simon Kamronn, Ulrich Paquet, Ole Winther

Conference: Advances in Neural Information Processing Systems

We introduce the Kalman variation of the auto-encoder, a framework for unsupervised learning of sequential data that disentangles two latent representations: an object's representation, coming from a recognition model, and a latent state describing its dynamics.

As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate high dimensional frames at each time step. The model is trained end-to-end on videos of various simulated physical systems and outperforms competing methods in generative and missing data imputation tasks.


More from Raffle