Despite its great success, machine learning can have its limits when dealing with insufficient
training data. A potential solution is the additional integration of prior knowledge into the …

Despite the sudden rise of AI, it still leaves a question mark to many newcomers on its
widespread adoption as it exhibits a lack of robustness and interpretability. For instance, the …

Collaborative learning (CL) can be a powerful method for sharing understanding between
learners. To this end, strategic regulation of processes, such as cognition and affect …

Background Modeling of gene regulatory networks (GRNs) is limited due to a lack of direct
measurements of genome-wide transcription factor activity (TFA) making it difficult to …

I examine the construction and evaluation of machine learning (ML) binary classification
models. These models are increasingly used for societal applications such as classifying …

Mit dem durchschlagenden Erfolg von tiefen neuronalen Netzen (s. Abschnitt 11.3), die zwar
oft sehr genaue Vorhersagen liefern, aber keine unmittelbare Einsicht in die gelernten …

Learning the deterioration of a battery from charge and discharge data is associated with
different non-random uncertainties. A specific methodology is developed, capable of …

Collecting or generating needed training data for data-driven Inverse Design (ID) can often
be cost-prohibitive. The ID data costs for aerodynamic shape optimization are the case …

Automatically designing or finding novel devices that accomplish new or existing functions
remains one of the greatest unsolved problems in Design Automation. In part, this is due to …

This thesis studies the reliability of deep neural networks using rare-event simulation
algorithms in the context of statistical reliability engineering. The aim is to assess the …