TY - CONF AU - Decke, Jens AU - Jenß, Arne AU - Sick, Bernhard AU - Gruhl, Christian A2 - T1 - An Efficient Multi Quantile Regression Network with Ad Hoc Prevention of Quantile Crossing T2 - International Conference on Architecture of Computing Systems (ARCS) PB - Springer CY - PY - 2024/ M2 - VL - IS - SP - EP - UR - M3 - KW - imported KW - itegpub KW - isac-www KW - QuantileRegression KW - QuantileCrossing KW - OrganicComputing KW - Self-Awareness KW - DifferentiableSorting L1 - SN - N1 - N1 - AB - This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency. Integrating ad hoc sorting in training, the SCQRNN ensures non-intersecting quantiles, boosting model reliability and interpretability. We demonstrate that the SCQRNN not only prevents quantile crossing and reduces computational complexity but also achieves faster convergence than traditional models. This advancement meets the requirements of high-performance computing for sustainable, accurate computation. In organic computing, the SCQRNN enhances self-aware systems with predictive uncertainties, enriching applications across finance, meteorology, climate science, and engineering. ER - TY - JOUR AU - Heidecker, Florian AU - El-Khateeb, Ahmad AU - Bieshaar, Maarten AU - Sick, Bernhard T1 - Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation JO - arXiv e-prints PY - 2024/ VL - IS - SP - EP - UR - https://arxiv.org/abs/2404.11266 M3 - KW - imported KW - itegpub KW - isac-www L1 - SN - N1 - N1 - AB - The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function. ER - TY - BOOK AU - A2 - Tomforde, Sven A2 - Krupitzer, Christian T1 - Organic Computing -- Doctoral Dissertation Colloquium 2023 PB - kassel university press AD - PY - 2024/ VL - 26 IS - SP - EP - UR - M3 - 10.17170/kobra-202402269661 KW - imported KW - itegpub KW - isac-www L1 - SN - N1 - N1 - AB - ER - TY - BOOK AU - A2 - Tomforde, Sven A2 - Krupitzer, Christian T1 - Organic Computing -- Doctoral Dissertation Colloquium 2022 PB - kassel university press AD - PY - 2023/ VL - 24 IS - SP - EP - UR - M3 - 10.17170/kobra-202302107484 KW - imported KW - itegpub KW - isac-www L1 - SN - N1 - N1 - AB - ER - TY - JOUR AU - Pham, Tuan AU - Kottke, Daniel AU - Krempl, Georg AU - Sick, Bernhard T1 - Stream-based active learning for sliding windows under the influence of verification latency JO - Machine Learning PY - 2022/ VL - 111 IS - 6 SP - 2011 EP - 2036 UR - M3 - doi.org/10.1007/s10994-021-06099-z KW - imported KW - itegpub KW - isac-www L1 - SN - N1 - N1 - AB - Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency. ER -