Publica
Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten. On Learning a Control System without Continuous Feedback
| ESANN 2020, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Proceedings : Online Event, October 2-4, 2020
Louvain-La-Neuve: i6doc.com publication, 2020
ISBN: 978-2-87587-074-2
pp.109-114 |
| European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) <28, 2020, Online> |
| Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01IS18038A/B/C; ML2R |
|
| English |
| Conference Paper, Electronic Publication |
| Fraunhofer IAIS () |
Abstract
We discuss a class of control problems by means of deep neural networks (DNN). Our goal is to develop DNN models that, once trained, are able to produce solutions of such problems at an acceptable error-rate and much faster computation time than an ordinary numerical solver. In the present note we study two such models for the Brockett integrator control problem.