Variational Predictive Routing with Nested Subjective Timescales

by   Alexey Zakharov, et al.

Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore hierarchical generative models that can flexibly adapt their layerwise representations in response to datasets with different temporal dynamics. Here, we present Variational Predictive Routing (VPR) - a neural probabilistic inference system that organizes latent representations of video features in a temporal hierarchy, based on their rates of change, thus modeling continuous data as a hierarchical renewal process. By employing an event detection mechanism that relies solely on the system's latent representations (without the need of a separate model), VPR is able to dynamically adjust its internal state following changes in the observed features, promoting an optimal organisation of representations across the levels of the model's latent hierarchy. Using several video datasets, we show that VPR is able to detect event boundaries, disentangle spatiotemporal features across its hierarchy, adapt to the dynamics of the data, and produce accurate time-agnostic rollouts of the future. Our approach integrates insights from neuroscience and introduces a framework with high potential for applications in model-based reinforcement learning, where flexible and informative state-space rollouts are of particular interest.


page 5

page 8

page 16

page 17


Neural Point Process for Learning Spatiotemporal Event Dynamics

Learning the dynamics of spatiotemporal events is a fundamental problem....

Variational Temporal Abstraction

We introduce a variational approach to learning and inference of tempora...

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

In this work, we take a representation learning perspective on hierarchi...

Learning the Predictability of the Future

We introduce a framework for learning from unlabeled video what is predi...

Automatic formation of the structure of abstract machines in hierarchical reinforcement learning with state clustering

We introduce a new approach to hierarchy formation and task decompositio...

A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction

In this paper we developed a hierarchical network model, called Hierarch...

ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning

Learning predictive models for unlabeled spatiotemporal data is challeng...