P
Philipp Becker
Researcher at Karlsruhe Institute of Technology
Publications - 19
Citations - 83
Philipp Becker is an academic researcher from Karlsruhe Institute of Technology. The author has contributed to research in topics: Computer science & Kalman filter. The author has an hindex of 3, co-authored 9 publications receiving 43 citations.
Papers
More filters
Proceedings Article
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
Philipp Becker,Harit Pandya,Gregor H. W. Gebhardt,Cheng Zhao,C. James Taylor,Gerhard Neumann +5 more
TL;DR: This work proposes a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations and uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions.
Proceedings Article
Expected Information Maximization: Using the I-Projection for Mixture Density Estimation
TL;DR: In this article, a variational upper bound to the I-projection objective is proposed to decompose the original objective into single objectives for each mixture component as well as for the coefficients.
Posted Content
Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning
Vaisakh Shaj,Philipp Becker,Dieter Büchler,Harit Pandya,Niels van Duijkeren,C. James Taylor,Marc Hanheide,Gerhard Neumann +7 more
TL;DR: Two architectures are presented, one for forward model learning and one for inverse model learning, which significantly outperform existing model learning frameworks as well as analytical models in terms of prediction performance on a variety of real robot dynamics models.
Posted Content
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
Philipp Becker,Harit Pandya,Gregor H. W. Gebhardt,Cheng Zhao,C. James Taylor,Gerhard Neumann +5 more
TL;DR: The Recurrent Kalman Network (RKN) as mentioned in this paper uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions.
Journal ArticleDOI
On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning
Philipp Becker,Gerhard Neumann +1 more
TL;DR: An alternative approach building on well-understood components for modeling aleatoric and epistemic uncertainty, dubbed Variational Recurrent Kalman Network (VRKN) is proposed, which uses Kalman updates for exact smoothing inference in a latent space and Monte Carlo Dropout to model epistem uncertainty.