4 Dokumente gefunden
Anomaly Detection Towards Modelling with Outlier Robustness
Machine learning algorithms have evolved in numerous fields into an important enabler for today's society. Thereby, anomaly detection is one of the machine learning tasks which contributes to many application domains. Anomalies, also known as outliers, can thereby be of advantageous but also of detrimental…
Exploring Methods of Explainable AI : Data-driven Attribution of Climate Events
In this work, we explore methods of explainable AI (xAI) to better understand how artificial neural networks (ANNs) come to their conclusion and to visualize the relationship between input and output. Moreover, we aim to use our insights to improve our understanding of the climate system. Working with…
Kiel: Self-Publishing of Department of Computer Science, 2023
Representation Learning for Texts and Graphs : A Unified Perspective on Efficiency, Multimodality, and Adaptability
[...] This thesis is situated between natural language processing and graph representation learning and investigates selected connections. First, we introduce matrix embeddings as an efficient text representation sensitive to word order. [...] Experiments with ten linguistic probing tasks, 11 supervised,…
Kiel: Self-Publishing of Department of Computer Science, 2023
Concept maps to enable interdisciplinary research in cross-domain fusion
A sound basis for an interdisciplinary dialogue is highly important for cross-domain fusion (CDF) dealing with knowledge transfer between working groups situated in different research disciplines. In this paper, we present a literature-based concept map as one example to start an interdisciplinary dialogue…