Mathematisch-Naturwissenschaftliche Fakultät: Suche
Anzeige der Dokumente 331-340 von 354
Practical Models for Sequential Decision Making in Natural Language Processing and Reinforcement Learning
(2023-11-17)
This thesis focuses on sequential decision and prediction (SDP) tasks, comprising structured prediction (SP) and reinforcement learning (RL) tasks. These tasks are characterized by generation of sequential outputs that ......
Informed Machine Learning: Integrating Prior Knowledge into Data-Driven Learning Systems
(2023-11-14)
Machine Learning is an important method in Artificial Intelligence (AI). It has shown great success in building models for tasks like prediction or image recognition by learning from patterns in large amounts of data. ...
Explainable Resource-Aware Representation Learning via Semantic Similarity
(2023-12-12)
The rapid advancement of artificial intelligence (AI) systems in recent years is largely due to the impressive capabilities of artificial neural networks. Their powerful capabilities in natural language understanding and ...
Approaching Partial Differential Equations with Physics-Driven Deep Learning
(2023-12-14)
Partial Differential Equations (PDEs) play an important role in describing continuous physical systems such as fluids, air-flows, waves and many more. Thus, by solving these equations, one can simulate smoke and water ...
Utilizing Constrained Homomorphisms in the Design of Efficient Graph Kernels
(2024-01-16)
Learning on graphs, particularly graph classification, requires rich graph representations. A common paradigm to obtain these is by extracting sets of substructures and representing graphs by such sets. The obtained graph ...
Deep Generative Modelling in Systems Medicine: From Transcriptomics Data to Drug Development
(2024-02-02)
(noch nicht zugänglich / not yet accessible)
Maßgeschneiderte nutzbarkeitserhaltende Pseudonymisierung: Anforderungen, Beschreibung, Umsetzung
(2023-01-30)
Die Verarbeitung personenbezogener Daten ist omnipräsent. Um die Privatsphäre und die informationelle Selbstbestimmung der Betroffenen zu achten, ist das Ergreifen von Maßnahmen zum Schutze der Vertraulichkeit der Daten ...
Theoretical and Practical Aspects of Finite Closure Systems for Mining and Learning
(2023-10-04)
This thesis investigates the potential and limitations of different adaptations of half-space separations in ordinary Euclidean spaces, one of the most popular paradigms in machine learning, to abstract finite closure ...
Adapting OpenCourseWare Based on the Needs and Preferences of Disabled Learners
(2022-12-22)
OpenCourseWare (OCW) systems are becoming a significant source of learning that are widely used for various educational purposes. With the COVID-19 Pandemic situation, these resources showed the impact of having material ...
Approximations for Hierarchical and Lower-Bounded Clustering and the Complexity of Minimum-Error Triangulation
(2024-03-28)
Clustering deals with the problem of finding structures in data. Given a number k we search for a good partition of a set of data points into at most k sets, where the sets of the partition are called clusters. In the ...