activity
20132022
most citedUnsupervised Real-Time Control through Variational Empowerment

11 citations · 32 across the 8 of their papers we have counts for

collaborators
Showing stat.MLShow all

9 papers · 1 filter

stat.ML2020

Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF

Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt +1

We solve the problem of 6-DoF localisation and 3D dense reconstruction in spatial environments as approximate Bayesian inference in a deep state-space model. Our approach leverages…

stat.ML2020

Learning Flat Latent Manifolds with VAEs

Nutan Chen, Alexej Klushyn, Francesco Ferroni +2

Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, w…

stat.ML20193 cited

Variational Tracking and Prediction with Generative Disentangled State-Space Models

Adnan Akhundov, Maximilian Soelch, Justin Bayer +1

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separ…

stat.ML2019

Increasing the Generalisation Capacity of Conditional VAEs

Alexej Klushyn, Nutan Chen, Botond Cseke +2

We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost. The framework of conditional var…

stat.ML2019

On Deep Set Learning and the Choice of Aggregations

Maximilian Soelch, Adnan Akhundov, Patrick van der Smagt +1

Recently, it has been shown that many functions on sets can be represented by sum decompositions. These decompositons easily lend themselves to neural approximations, extending the…

stat.ML201911 cited

Bayesian Learning of Neural Network Architectures

Georgi Dikov, Patrick van der Smagt, Justin Bayer

In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distribu…