-
Semi-Amortized Variational Autoencoders
Amortized variational inference (AVI) replaces instance-specific local i...
read it
-
Meta-Amortized Variational Inference and Learning
How can we learn to do probabilistic inference in a way that generalizes...
read it
-
Approximate Bayesian inference in spatial environments
We propose to learn a stochastic recurrent model to solve the problem of...
read it
-
Variational Tracking and Prediction with Generative Disentangled State-Space Models
We address tracking and prediction of multiple moving objects in visual ...
read it
-
Variational Nonlinear System Identification
This paper considers parameter estimation for nonlinear state-space mode...
read it
-
PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference
In the present paper, we propose an extension of the Deep Planning Netwo...
read it
-
Learning Variational Data Assimilation Models and Solvers
This paper addresses variational data assimilation from a learning point...
read it
Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
We solve the problem of 6-DoF localisation and 3D dense reconstruction in spatial environments as approximate Bayesian inference in a deep generative approach which combines learned with engineered models. This principled treatment of uncertainty and probabilistic inference overcomes the shortcoming of current state-of-the-art solutions to rely on heavily engineered, heterogeneous pipelines. Variational inference enables us to use neural networks for system identification, while a differentiable raycaster is used for the emission model. This ensures that our model is amenable to end-to-end gradient-based optimisation. We evaluate our approach on realistic unmanned aerial vehicle flight data, nearing the performance of a state-of-the-art visual inertial odometry system. The applicability of the learned model to downstream tasks such as generative prediction and planning is investigated.
READ FULL TEXT
Comments
There are no comments yet.