Recurrent Ladder Networks
This work addresses the need for architectures that combine iterative inference with temporal modeling for complex learning tasks in domains like video and music.
The authors tackled the problem of learning hierarchical abstractions and handling temporal information by proposing a recurrent extension of Ladder networks, achieving close-to-optimal results on video data modeling, competitive results on music modeling, and improved perceptual grouping.
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling. The architecture shows close-to-optimal results on temporal modeling of video data, competitive results on music modeling, and improved perceptual grouping based on higher order abstractions, such as stochastic textures and motion cues. We present results for fully supervised, semi-supervised, and unsupervised tasks. The results suggest that the proposed architecture and principles are powerful tools for learning a hierarchy of abstractions, learning iterative inference and handling temporal information.