Bayesian Learning
Dynamic Bottleneck for Robust Self-Supervised Exploration
However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle.
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
However, most systems of practical interest are non-linear, requiring more complex models. Many approximate inference methods have been developed for non-linear dynamical systems: Deterministic methods approximate the filtering and smoothing distributions e.g. by using a Taylor series
Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent Priyank Jaini Bosch-Delta Lab University of Amsterdam Lars Holdijk
We first introduce Equivari-ant Stein V ariational Gradient Descent algorithm - an equivariant sampling method based on Stein's identity for sampling from densities with symmetries.
Uncertainty-Driven Loss for Single Image Super-Resolution
How to achieve such spatial adaptation in a principled manner has been an open problem in both traditional model-based and modern learning-based approaches toward SISR. In this paper, we propose a new adaptive weighted loss for SISR to train deep networks focusing on challenging situations such as textured and edge pixels with high uncertainty.
A Variational Approach for Learning from Positive and Unlabeled Data Hui Chen
However, such a method easily leads to severe overfitting.
