Refine
Departments, institutes and facilities
- Fachbereich Wirtschaftswissenschaften (89)
- Fachbereich Informatik (65)
- Fachbereich Angewandte Naturwissenschaften (59)
- Fachbereich Ingenieurwissenschaften und Kommunikation (58)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (50)
- Fachbereich Sozialpolitik und Soziale Sicherung (46)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (23)
- Institut für Verbraucherinformatik (IVI) (17)
- Institut für Medienentwicklung und -analyse (IMEA) (16)
- Institut für funktionale Gen-Analytik (IFGA) (16)
Document Type
- Article (142)
- Part of a Book (69)
- Conference Object (66)
- Book (monograph, edited volume) (20)
- Preprint (12)
- Contribution to a Periodical (8)
- Report (8)
- Research Data (6)
- Doctoral Thesis (6)
- Master's Thesis (6)
Year of publication
- 2022 (365) (remove)
Keywords
- Machine Learning (5)
- Lehrbuch (4)
- Medienästhetik (4)
- virtual reality (4)
- Cathepsin K (3)
- GDPR (3)
- Knowledge Graphs (3)
- Lignin (3)
- Medien (3)
- Medienwissenschaft (3)
Auswirkungen einer anhaltenden, inflationären Geldpolitik in der Eurozone auf den privaten Sparer
(2022)
Die vorliegende Bachelorarbeit setzt sich kritisch mit den Auswirkungen einer anhaltenden, inflationären Geldpolitik in der Eurozone auf den privaten Sparer auseinander. Im Rahmen dieser Arbeit wird aufgezeigt, wie die starke Erhöhung der Geldmenge Einfluss auf die Möglichkeiten und Entscheidungen des Sparers hat und wie weit eine solche Geldpolitik mit den Interessen des Sparers vereinbar ist.
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve perception capabilities such as sonar image classification. Due to the confidential nature of sonar imaging and the difficulty to interpret sonar images, it is challenging to create public large labeled sonar datasets to train supervised learning algorithms. In this work, we investigate the potential of three self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn high-quality sonar image representation without the need of human labels. We present pre-training and transfer learning results on real-life sonar image datasets. Our results indicate that self-supervised pre-training yields classification performance comparable to supervised pre-training in a few-shot transfer learning setup across all three methods. Code and self-supervised pre-trained models are be available at https://github.com/agrija9/ssl-sonar-images
We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums.