191 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Volkswagen Group (Germany)DE10 papers
- Technical University of MunichDE6 papers
- Data:Lab Munich (Germany)DE4 papers
- Ludwig-Maximilians-Universität MünchenDE3 papers
- Leiden UniversityNL2 papers
- OTH RegensburgDE2 papers
- Barcelona Institute of Science and TechnologyES1 paper
- Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)DE1 paper
- Freie Universität BerlinDE1 paper
- Institute of Photonic SciencesES1 paper
- Institute of Science and Technology1 paper
- Johns Hopkins UniversityUS1 paper
3 papers · 1 filter
Latent Matters: Learning Deep State-Space Models
Alexej Klushyn, Richard Kurle, Maximilian Soelch +2
Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower b…
Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison
Lukas Brunke, Prateek Agrawal, Nikhil George
Input perturbation methods occlude parts of an input to a function and measure the change in the function's output. Recently, input perturbation methods have been applied to genera…
Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
Justin Bayer, Maximilian Soelch, Atanas Mirchev +2
Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO). In this setting, variational posteriors are often on…