no code implementations • NeurIPS 2021 • Alexej Klushyn, Richard Kurle, Maximilian Soelch, Botond Cseke, Patrick van der Smagt
Our results show that the constrained optimisation framework significantly improves system identification and prediction accuracy on the example of established state-of-the-art DSSMs.
no code implementations • ICLR 2021 • Justin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt
Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO).
no code implementations • 14 Oct 2019 • Adnan Akhundov, Maximilian Soelch, Justin Bayer, Patrick van der Smagt
We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model.
no code implementations • 18 Mar 2019 • Maximilian Soelch, Adnan Akhundov, Patrick van der Smagt, Justin Bayer
Recently, it has been shown that many functions on sets can be represented by sum decompositions.
no code implementations • 18 May 2018 • Atanas Mirchev, Baris Kayalibay, Maximilian Soelch, Patrick van der Smagt, Justin Bayer
Model-based approaches bear great promise for decision making of agents interacting with the physical world.
no code implementations • 13 Oct 2017 • Maximilian Karl, Maximilian Soelch, Philip Becker-Ehmck, Djalel Benbouzid, Patrick van der Smagt, Justin Bayer
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control.
4 code implementations • 20 May 2016 • Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt
We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models.
no code implementations • 23 Feb 2016 • Maximilian Soelch, Justin Bayer, Marvin Ludersdorfer, Patrick van der Smagt
Approximate variational inference has shown to be a powerful tool for modeling unknown complex probability distributions.