TY - JOUR A1 - Beimler, Josef A1 - Leißl, Caroline A1 - Ebner, Lena A1 - Elsner, Michael A1 - Mühlbauer, Gerhard A1 - Kohlert, Dieter A1 - Schubert, Martin J. W. A1 - Weiß, Andreas P. A1 - Sterner, Michael A1 - Raith, Thomas A1 - Afranseder, Martin A1 - Krapf, Tobias A1 - Mottok, Jürgen A1 - Siemers, Christian A1 - Großmann, Benjamin A1 - Höcherl, Johannes A1 - Schlegl, Thomas A1 - Schneider, Ralph A1 - Milaev, Johannes A1 - Rampelt, Christina A1 - Roduner, Christian A1 - Glowa, Christoph A1 - Bachl, Christoph A1 - Schliekmann, Claus A1 - Gnan, Alfons A1 - Grill, Martin A1 - Ruhland, Karl A1 - Piehler, Thomas A1 - Friers, Daniel A1 - Wels, Harald A1 - Pflug, Kenny A1 - Kucera, Markus A1 - Waas, Thomas A1 - Schlachetzki, Felix A1 - Boy, Sandra A1 - Pemmerl, Josef A1 - Leis, Alexander A1 - Welsch, Andreas F.X. A1 - Graf, Franz A1 - Zenger, Gerhard A1 - Volbert, Klaus A1 - Waas, Thomas A1 - Scherzinger, Stefanie A1 - Klettke, Meike A1 - Störl, Uta A1 - Heyl, C. A1 - Boldenko, A. A1 - Monkman, Gareth J. A1 - Kujat, Richard A1 - Briem, Ulrich A1 - Hierl, Stefan A1 - Talbot, Sebastian A1 - Schmailzl, Anton A1 - Ławrowski, Robert Damian A1 - Prommesberger, Christian A1 - Langer, Christoph A1 - Dams, Florian A1 - Schreiner, Rupert A1 - Valentino, Piergiorgio A1 - Romano, Marco A1 - Ehrlich, Ingo A1 - Furgiuele, Franco A1 - Gebbeken, Norbert A1 - Eisenried, Michael A1 - Jungbauer, Bastian A1 - Hutterer, Albert A1 - Bauhuber, Michael A1 - Mikrievskij, Andreas A1 - Argauer, Monika A1 - Hummel, Helmut A1 - Lechner, Alfred A1 - Liebetruth, Thomas A1 - Schumm, Michael A1 - Joseph, Saskia A1 - Reschke, Michael A1 - Soska, Alexander A1 - Schroll-Decker, Irmgard A1 - Putzer, Michael A1 - Rasmussen, John A1 - Dendorfer, Sebastian A1 - Weber, Tim A1 - Al-Munajjed, Amir Andreas A1 - Verkerke, Gijsbertus Jacob A1 - Renkawitz, Tobias A1 - Haug, Sonja A1 - Rudolph, Clarissa A1 - Zeitler, Annika A1 - Schaubeck, Simon A1 - Steffens, Oliver A1 - Rechenauer, Christian A1 - Schulz-Brize, Thekla A1 - Fleischmann, Florian A1 - Kusterle, Wolfgang A1 - Beer, Anne A1 - Wagner, Bernd A1 - Neidhart, Thomas ED - Baier, Wolfgang T1 - Forschungsbericht 2013 T3 - Forschungsberichte der OTH Regensburg - 2013 Y1 - 2014 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-7990 CY - Regensburg ER - TY - JOUR A1 - Appelhans, Marie-Luise A1 - Kampmann, Matthias A1 - Mottok, Jürgen A1 - Riederer, Michael A1 - Nagl, Klaus A1 - Steffens, Oliver A1 - Dünnweber, Jan A1 - Wildgruber, Markus A1 - Roth, Julius A1 - Stadler, Timo A1 - Palm, Christoph A1 - Weiß, Martin Georg A1 - Rochholz, Sandra A1 - Bierl, Rudolf A1 - Gschossmann, Andreas A1 - Haug, Sonja A1 - Schmidbauer, Simon A1 - Koch, Anna A1 - Westner, Markus A1 - Bary, Benedikt von A1 - Ellermeier, Andreas A1 - Vögele, Daniel A1 - Maiwald, Frederik A1 - Hierl, Stefan A1 - Schlamp, Matthias A1 - Ehrlich, Ingo A1 - Siegl, Marco A1 - Hüntelmann, Sven A1 - Wildfeuer, Matthias A1 - Brückl, Oliver A1 - Sterner, Michael A1 - Hofrichter, Andreas A1 - Eckert, Fabian A1 - Bauer, Franz A1 - Dawoud, Belal A1 - Rabl, Hans-Peter A1 - Gamisch, Bernd A1 - Schmidt, Ottfried A1 - Heberl, Michael A1 - Thema, Martin A1 - Mayer, Ulrike A1 - Eller, Johannes A1 - Sippenauer, Thomas A1 - Adelt, Christian A1 - Haslbeck, Matthias A1 - Vogl, Bettina A1 - Mauerer, Wolfgang A1 - Ramsauer, Ralf A1 - Lohmann, Daniel A1 - Sax, Irmengard A1 - Gabor, Thomas A1 - Feld, Sebastian A1 - Linnhoff-Popien, Claudia A1 - Ławrowski, Robert Damian A1 - Langer, Christoph A1 - Schreiner, Rupert A1 - Sellmair, Josef ED - Baier, Wolfgang T1 - Forschung 2019 BT - Thema: Künstliche Intelligenz N2 - Bericht mit Forschungsprojekten aus verschiedenen Bereichen der OTH Regensburg mit dem Schwerpunktthema "Künstliche Intelligenz" und einem Gespräch zur "Medizin der Zukunft" T3 - Forschungsberichte der OTH Regensburg - 2019 KW - Forschung KW - Forschungsbericht KW - Künstliche Intelligenz Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-7890 SN - 978-3-9818209-7-3 CY - Regensburg ER - TY - INPR A1 - Bock, Sebastian A1 - Weiß, Martin Georg T1 - Local Convergence of Adaptive Gradient Descent Optimizers N2 - Adaptive Moment Estimation (ADAM) is a very popular training algorithm for deep neural networks and belongs to the family of adaptive gradient descent optimizers. However to the best of the authors knowledge no complete convergence analysis exists for ADAM. The contribution of this paper is a method for the local convergence analysis in batch mode for a deterministic fixed training set, which gives necessary conditions for the hyperparameters of the ADAM algorithm. Due to the local nature of the arguments the objective function can be non-convex but must be at least twice continuously differentiable. Then we apply this procedure to other adaptive gradient descent algorithms and show for most of them local convergence with hyperparameter bounds. KW - ADAM Optimizer KW - Convergence KW - momentum method KW - dynamical system KW - fixed point Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-7546 ER - TY - INPR A1 - Bock, Sebastian A1 - Weiß, Martin Georg T1 - Rotation Detection of Components with Convolutional Neural Networks N2 - The main issues in many image processing applications are object recognition and detection of objects, which answers the questions whether an object is present and if it is present, where it is located. Popular object detection algorithms like YOLO use a regression formulation for the whole problem, especially for the bounding box parameters. In production industry the setting usually is different: One usually knows the object type and rather wants to know with high precision where the object is. We study a prototype application in this area where we identify the rotation of an object in a plane. To solve this problem use a regression approach with a CNN architecture as a function approximator. We compare our results to standard image processing algorithms, which do not use neural networks, and present quantitative results on the accuracy. CNNs seem at least competitive to classical image processing. KW - Neural networks KW - Network Architecture KW - CNN KW - Functionapproximation KW - Image orientation Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-4120 ER - TY - CHAP A1 - Bock, Sebastian A1 - Weiß, Martin Georg T1 - Non-Convergence and Limit Cycles in the Adam Optimizer T2 - Proceedings of the 28th International Conference on Artificial Neural Networks, 2019, Munich, Germany, September 17-19 N2 - One of the most popular training algorithms for deep neural networks is the Adaptive Moment Estimation (Adam) introduced by Kingma and Ba. Despite its success in many applications there is no satisfactory convergence analysis: only local convergence can be shown for batch mode under some restrictions on the hyperparameters, counterexamples exist for incremental mode. Recent results show that for simple quadratic objective functions limit cycles of period 2 exist in batch mode, but only for atypical hyperparameters, and only for the algorithm without bias correction. We extend the convergence analysis to all choices of the hyperparameters for quadratic functions. This finally answers the question of convergence for Adam in batch mode to the negative. We analyze the stability of these limit cycles and relate our analysis to other results where approximate convergence was shown, but under the additional assumption of bounded gradients which does not apply to quadratic functions. The investigation heavily relies on the use of computer algebra due to the complexity of the equations. KW - Adam optimizer KW - Convergence KW - Computer algebra KW - Dynamical system KW - Limit cycle KW - Neuronales Netz KW - Maschinelles Lernen KW - Optimierungsalgorithmus KW - Konvergenz 〈Informationstechnik〉 KW - Computeralgebra Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-490 UR - https://doi.org/10.1007/978-3-030-30484-3_20 SP - 232 EP - 243 ER - TY - CHAP A1 - Bock, Sebastian A1 - Weiß, Martin Georg T1 - A Proof of Local Convergence for the Adam Optimizer T2 - Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), 2019, Budapest, Hungary, July 14-19 N2 - Adaptive Moment Estimation (Adam) is a very popular training algorithm for deep neural networks, implemented in many machine learning frameworks. To the best of the authors knowledge no complete convergence analysis exists for Adam. The contribution of this paper is a method for the local convergence analysis in batch mode for a deterministic fixed training set, which gives necessary conditions for the hyperparameters of the Adam algorithm. Due to the local nature of the arguments the objective function can be non-convex but must be at least twice continuously differentiable. KW - Non-convex optimization KW - Adam optimizer KW - Convergence KW - Momentum method KW - Dynamical system KW - Fixed point KW - Neuronales Netz KW - Maschinelles Lernen KW - Optimierungsalgorithmus KW - Konvergenz 〈Informationstechnik〉 Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-501 UR - https://doi.org/10.1109/IJCNN.2019.8852239 VL - 2019 SP - 1 EP - 8 ER - TY - INPR A1 - Weiß, Martin Georg T1 - Optimization of Cartesian Tasks with Configuration Selection N2 - A basic task in the design of an industrial robot application is the relative placement of robot and workpiece. Process points are defined in Cartesian coordinates relative to the workpiece coordinate system, and the workpiece has to be located such that the robot can reach all points. Finding such a location is still an iterative procedure based on the developers' intuition. One difficulty is the choice of one of the several solutions of the backward transform of a typical 6R robot. We present a novel algorithm that simultaneously optimizes the workpiece location and the robot configuration at all process points using higher order optimization algorithms. A key ingredient is the extension of the robot with a virtual prismatic axis. The practical feasibility of the approach is shown with an example using a commercial industrial robot. KW - optimization KW - Intralogistik KW - Industrieroboter KW - Programmgenerierung KW - Nichtlineare Optimierung KW - robotics Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-20176 UR - https://arxiv.org/pdf/1811.07137.pdf ER - TY - CHAP A1 - Schubert, Martin J. W. A1 - Seign, Stefan A1 - Dai, Q. A1 - Hinterseer, Sebastian A1 - Pielmeier, F. A1 - Pietsch, Alexander A1 - Seebauer, C. A1 - Weiß, Josef A1 - Yu, C. A1 - Zenger, Stefan T1 - Capacitive Sensor Technology for Soil Moisture Monitoring Networks T2 - 24th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 5-8 Dec. 2017, Batumi, Georgia N2 - A sensor technology for tracking soil-moisture in agricultural fields is presented. A linear measurement method was developed to satisfy the need for cheap sensors with wide range of capacitance change such as factor 30. A combined wired and wireless network transmits data to a server. Various battery aspects are compared with respect to use in agriculture. Y1 - 2017 U6 - https://doi.org/10.1109/ICECS.2017.8292018 SP - 190 EP - 193 ER - TY - CHAP A1 - Weiß, Martin Georg ED - Holderbaum, William ED - Selig, J. M. T1 - Optimization of Cartesian Tasks with Configuration Selection T2 - 2nd IMA Conference on Mathematics of Robotics: online September 8–10, 2021 N2 - A basic task in the design of an industrial robot application is the relative placement of robot and workpiece. Process points are defined in Cartesian coordinates relative to the workpiece coordinate system, and the workpiece has to be located such that the robot can reach all points. Finding such a location is still an iterative procedure based on the developers’ intuition. One difficulty is the choice of one of the several solutions of the backward transform of a typical 6R robot. We present a novel algorithm that simultaneously optimizes the workpiece location and the robot configuration at all process points using higher order optimization algorithms. A key ingredient is the extension of the robot with a virtual prismatic axis. The practical feasibility of the approach is shown with an example using a commercial industrial robot. KW - Configuration KW - Differentiable optimization KW - Virtual axis Y1 - 2022 SN - 978-3-030-91351-9 U6 - https://doi.org/10.1007/978-3-030-91352-6_16 SP - 153 EP - 160 PB - Springer International Publishing CY - Cham ER - TY - CHAP A1 - Weiß, Martin Georg A1 - Volbert, Klaus ED - Falter, Thomas T1 - Intelligente Steuerung von Industrierobotern T2 - Zweite OTH-Clusterkonferenz 18. Januar 2017 Techbase, Regensburg Y1 - 2017 CY - Regensburg ER -