TY - CHAP A1 - Schönmann, Alexander A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Dumitrescu, Roman ED - Hölzle, Katharina T1 - KI-Augmentation der Reifegradbewertung von Technologien: Können KI-Sprachmodelle Expertenwissen ersetzen? T2 - Vorausschau und Technologieplanung: 17. Symposium für Vorausschau und Technologieplanung, 14. und 15. September 2023, Berlin UR - https://doi.org/10.17619/UNIPB/1-1821 Y1 - 2023 UR - https://doi.org/10.17619/UNIPB/1-1821 SN - 978-3-947647-32-3 SP - 371 EP - 387 PB - Universität Paderborn CY - Paderborn ER - TY - CHAP A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Kinnaird, Katherine M. ED - Steinbach, Peter ED - Guhr, Oliver T1 - A Deep Learning Bootcamp for Engineering & Management Students T2 - Proceedings of the Third Teaching Machine Learning and Artificial Intelligence Workshop Y1 - 2023 UR - https://proceedings.mlr.press/v207/lodes23a.html SP - 32 EP - 36 PB - PMLR CY - [s. l.] ER - TY - CHAP A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Do, Phuc ED - Michau, Gabriel ED - Ezhilarasu, Cordelia T1 - Certainty Groups: A Practical Approach to Distinguish Confidence Levels in Neural Networks T2 - Proceedings of the European Conference of the PHM Society 2022 N2 - Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting. UR - https://doi.org/10.36001/phme.2022.v7i1.3331 KW - machine Learning KW - classification KW - uncertainty KW - estimaton KW - neural network Y1 - 2022 UR - https://doi.org/10.36001/phme.2022.v7i1.3331 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-31307 SN - 978-1-936263-36-3 SP - 294 EP - 305 PB - PHM Society CY - State College ER - TY - CHAP A1 - Lodes, Lukas A1 - Schiendorfer, Alexander ED - Facchinetti, Tullio ED - Cenedese, Angelo ED - Lo Bello, Lucia ED - Vitturi, Stefano ED - Sauter, Thilo ED - Tramarin, Federico T1 - A multi-layer machine learning architecture for near real-time inference in manufacturing based on Apache Kafka and selective classification T2 - 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA) UR - https://doi.org/10.1109/ETFA61755.2024.10711030 Y1 - 2024 UR - https://doi.org/10.1109/ETFA61755.2024.10711030 SN - 979-8-3503-6123-0 PB - IEEE CY - Piscataway ER -