Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
Authors: Philipp Becker, Harit Pandya, Gregor Gebhardt, Cheng Zhao, C. James Taylor, Gerhard Neumann
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | As shown by our experiments, the RKN obtains much more accurate uncertainty estimates than an LSTM or Gated Recurrent Units (GRUs) (Cho et al., 2014) while also showing a slightly improved prediction performance and outperforms various recent generative models on an image imputation task. |
| Researcher Affiliation | Collaboration | 1Computational Learning for Autonomous Systems, TU Darmstadt, Darmstadt, Germany. 2Bosch Center for Artificial Intelligence, Renningen, Germany. 3University of T ubingen, T ubingen, Germany. 4Lincoln Center for Autonomous Systems, University of Lincoln, Lincoln, UK. 5Extreme Robotics Lab, University of Birmingham, Birmingham, UK. 6Engineering Department, Lancaster University, Lancaster, UK. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code is available online1. 1https://github.com/LCAS/RKN |
| Open Datasets | Yes | Next, we evaluate the RKN on the task of learning visual odometry from monocular images on the KITTI visual odometry dataset (Geiger et al., 2012). |
| Dataset Splits | No | The paper mentions training and testing on datasets but defers a 'full listing of hyperparameters and data set specifications' to the supplementary material. It does not provide explicit train/validation/test split percentages or sample counts in the main text. |
| Hardware Specification | No | The paper states, 'Calculations for this research were conducted on the Lichtenberg high performance computer of the TU Darmstadt,' but does not provide specific hardware details such as GPU/CPU models or memory. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The paper states, 'A full listing of hyperparameters and data set specifications can be found in the supplementary material,' indicating that these details are not provided in the main text. It mentions using 'Adam... with default parameters' but no concrete values. |