Eldorado - Repositorium der TU Dortmund

Ressourcen aus und für Forschung, Lehre und Studium

Bei diesem Service handelt es sich um das Institutionelle Repositorium der Technischen Universität Dortmund. Hier werden Ressourcen aus und für Lehre, Studium und Forschung gespeichert, erschlossen und der Öffentlichkeit zugänglich gemacht.

Hauptbereiche in Eldorado

Wählen Sie einen Bereich, um dessen Inhalt anzusehen.

Gerade angezeigt 1 - 5 von 9

Fach- und Universitätsübergreifendes 1319
Fakultäten 13868
Graduate School und Graduiertenkollegs 12
Hochschulverwaltung 1249
Sonderforschungsbereiche 1595

Aktuellste Veröffentlichungen

Eine valide Datengrundlage für die Kindertagesbetreuung
(2026-06) Meiner-Teubner, Christiane; Birkel-Barmsen, Janine; Carstens, Yannick; Kopp, Katharina
Uncertainly quantification for interpretable and reliable machine learning
(2026) Newen, Carina; Müller, Emmanuel; Hammer, Barbara
In the booming research field of machine learning and artificial intelligence, uncertainty quantification is often overlooked as an essential quality guarantee. When interacting with and applying artificial intelligence, it is common to evaluate the performance of such learners by metrics such as efficiency, accuracy and other task-specific performance-based metrics without emphasizing the importance of quantifying potential hazards. Uncertainty characterizes the proximity between observations and predictions, providing a measure of how well a model reflects the true underlying data distribution. This thesis places uncertainty quantification at the center of its investigation, and we investigate three interconnecting subareas:. Explanations and visualizations of uncertainties, robustness with regard to uncertainties, and trustworthiness and human interpretability of uncertainties. This interdisciplinary setup is crucial to establishing new connections between the domains. While each of the subjects has been extensively studied in isolation, it is often at the interconnections that new research paradigms emerge: Neural networks as we know them today are a result of a fusion of neuroscience-inspired models of cognition, mathematical formalization, and algorithmic innovation. Without the mathematical groundwork, the advances in computing power and the biological neuron inspiration, this new field of research would not exist today. By interweaving explanation, robustness and trust in the context of uncertainty, in this thesis, we aim to pave the way for engineering practical systems that are both reliable, interpretable, and ultimately trustworthy. In these three areas, we focus on empirical approaches and solutions for important research challenges. The first part of this thesis focuses on visualizing uncertainties of high-dimensional data in an unsupervised setting using the novel proxy for local intrinsic dimensionalities. Furthermore, we show limitations of popular explainable AI methods using a newly constructed open-source dataset that focuses on an ambiguous classification task. We use the proxy of local intrinsic dimensionality as a proxy for the likelihood of adversarial attacks, connecting uncertainties with robustness metrics. In the second part of the thesis, we delve more deeply into the robustness domain by proposing certainty attacks and discussing the independence of adversarial transferability to topological changes in the datasets. We discuss the origin of transferability and possible research directions for future work. The main motivation between the importance of uncertainties stems from the need to calibrate human trust---for the successful application of machine learners, we have to align the trust levels of humans according to their actual performance. This motivates the third part of the thesis, where we discuss trust in AI systems with a special emphasis on uncertainty quantification. Finally, we discuss open challenges regarding uncertainty quantification and outline future work in this particular domain, with special emphasis on explainable AI and robustness.
Generation of training data for handwritten text recognition using latent diffusion models
(2026) Brandenbusch, Kai Ingo Wilhelm; Fink, Gernot A.; Harmeling, Stefan
Handwritten documents have served as the predominant medium for the preservation and transmission of information. Numerous works aim at implementing automatic searchability and information extraction from such documents. Additionally, a research field has emerged that deals with the generation of handwritten words and documents. The task of handwritten text generation (HTG) constitutes the generation of a realistic looking image depicting a given string in a handwriting with a desired style. In particular, the correctness and readability of the generated word as well as the imitation of the desired style pose major challenges. Generative models such as generative adversarial networks and diffusion models have been adopted to approach this task. HTG offers the promising opportunity to generate annotated training data for other document analysis models. This is particularly interesting when training data is generated for a new target dataset for which no annotated examples are available. In this thesis, an HTG system based on a latent diffusion model for the generation of training data for handwritten text recognition models is proposed. In order to generate images for an unseen target dataset, a pretrained masked autoencoder is used to extract style encodings from a set of example images. Together with embeddings of the string to be generated, these encodings are used to condition the generation process using classifier-free guidance. In order to enhance the generation quality for styles from the target dataset, two semi-supervised training schemes for the HTG model are presented in this work. These training schemes enable the model to leverage information about new styles either from examples that are only annotated with writer IDs or from examples without any annotation. The obtained HTG system is used to generate a synthetic dataset which contains samples with handwriting styles similar to those in the target dataset. A handwriting recognition model is then trained on this stylized synthetic dataset. The experimental results demonstrate the successful application of the proposed HTG model for the generation of training data for a handwriting recognition model. Even if the HTG model is trained with a dataset other than the target dataset, it is shown that a recognition model can successfully be trained using only generated training samples. Furthermore, the experiments demonstrate that including unlabeled samples from the target dataset using the proposed semi-supervised training schemes results in considerable improvements of the recognition model trained on the generated data. In summary, the HTG system presented in this thesis offers a promising approach toward the generation of training data for unseen datasets and can facilitate the training of other document analysis models.
Chiral Pd2L4 capsules from readily accessible Tröger’s base ligands inducing circular dichroism on fullerenes C60 and C70
(Cambridge Crystallographic Data Centre, 2024-12-03) Benchimol, Elie; O’Connor, Helen M.; Schmidt, Björn; Bogo, Nicola; Holstein, Julian J.; Lovitt, June I.; Shanmugaraju, Sankarasekaran; Stein, Christopher J.; Gunnlaugsson, Thorfinnur; Clever, Guido H.
The induction of chirality on pristine fullerenes through non-covalent embedding in an asymmetric nano-confinement has only been rarely reported. Bringing molecules with such a unique electronic structure and broad application range into a chiral environment is particularly appealing for the development of chiroptical materials, enantioselective photoredox catalysts and systems showing chirality-induced spin selectivity (CISS). In this study, we report the formation of a chiral, configurationally stable Pd2L4 capsule assembled from a C2-symmetric, ‘ribbon-shaped’ ligand with a Tröger's base naphthalimide (TbNaps) backbone, easily synthesized in three steps from commercially available compounds. Embedding chirality directly into the ligand backbone ensures a relatively lightweight receptor design whose aromatic panels create a strongly shielded inner cavity of about 700 Å3 volume. Fullerenes C60 and C70, as well as a pair of corannulenes, can be bound in acetonitrile (where unsubstituted fullerenes are insoluble) and X-ray structures of host-guest complexes were obtained. Tight interactions between the chiral host and the fullerene guests leads to the induction of a circular dichroism (CD) on the characteristic absorption bands of the forbidden π–π* transitions of the fullerenes, backed up by sTDA TD-DFT calculations and detailed investigation of the electronic excited states.
Case study: flipped classroom with gamification in a hybrid fluid mechanics course
(Wiley, 2024-07-05) Boettcher, Konrad E. R.; Fischer, Michael‐David; Hellmich, Justus
A fluid mechanics course in process engineering designed according to the students’ wishes mixes lecture and exercise in co-teaching and flipped-classroom elements with gamification. The effectiveness increases as the number of points achieved in the exam increases by 31.9 % compared to the average of the four previous years. The withdrawal rate drops from 54.8 % to 17.4 % and the failure rate from 38.7 % to 23.7 %, which enhances efficiency. The students’ self-report shows a better preparation to the course sessions, but they do not feel stressed much additionally. About 80 % of the initially attending students participate at the end of the course.