no code implementations • 12 Mar 2024 • Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias Stähle, Daniel A. Keim, Oliver Deussen, Mennatallah El-Assady
Large language models (LLMs) are widely deployed in various downstream tasks, e. g., auto-completion, aided writing, or chat-based text generation.
no code implementations • 17 Oct 2023 • Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias Stähle, Daniel A. Keim, Oliver Deussen, Andreas Spitz, Mennatallah El-Assady
We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges.
1 code implementation • 6 Oct 2023 • Udo Schlegel, Daniel A. Keim
Given the increasing amount and general complexity of time series data in domains such as finance, weather forecasting, and healthcare, there is a growing need for state-of-the-art performance models that can provide interpretable insights into underlying patterns and relationships.
no code implementations • 14 Jul 2023 • Udo Schlegel, Daniela Oelke, Daniel A. Keim, Mennatallah El-Assady
To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels.
1 code implementation • 11 Jul 2023 • Udo Schlegel, Daniel A. Keim
This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +4
no code implementations • 7 Oct 2022 • Eugene Bykovets, Yannick Metz, Mennatallah El-Assady, Daniel A. Keim, Joachim M. Buhmann
To overcome this, we formulate a Pareto optimization problem in which we simultaneously optimize for reward and OOD detection performance.
Out of Distribution (OOD) Detection Reinforcement Learning (RL)
no code implementations • 22 Aug 2022 • Eugene Bykovets, Yannick Metz, Mennatallah El-Assady, Daniel A. Keim, Joachim M. Buhmann
Robustness to adversarial perturbations has been explored in many areas of computer vision.
1 code implementation • 31 May 2022 • Udo Schlegel, Samuel Schiegg, Daniel A. Keim
In many cases, such large networks are not deployable on particular hardware and need to be reduced in size.
no code implementations • 23 Mar 2022 • Matthias Miller, Julius Rauscher, Daniel A. Keim, Mennatallah El-Assady
Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information.
no code implementations • 27 Sep 2021 • Udo Schlegel, Daniel A. Keim
We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.
1 code implementation • 17 Sep 2021 • Udo Schlegel, Duy Vo Lam, Daniel A. Keim, Daniel Seebacher
Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances.
no code implementations • 11 May 2021 • Maximilian T. Fischer, Daniel A. Keim, Manuel Stein
With the increasingly detailed investigation of game play and tactics in invasive team sports such as soccer, it becomes ever more important to present causes, actions and findings in a meaningful manner.
no code implementations • 8 Dec 2020 • Udo Schlegel, Daniela Oelke, Daniel A. Keim, Mennatallah El-Assady
Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques.
BIG-bench Machine Learning Explainable Artificial Intelligence (XAI) +2
no code implementations • 1 Sep 2020 • Philipp Meschenmoser, Juri F. Buchmüller, Daniel Seebacher, Martin Wikelski, Daniel A. Keim
To close this gap, we present our MultiSegVA platform for interactively defining segmentation techniques and parameters on multiple temporal scales.
no code implementations • 16 Sep 2019 • Udo Schlegel, Hiba Arnout, Mennatallah El-Assady, Daniela Oelke, Daniel A. Keim
In this work, we apply XAI methods previously used in the image and text-domain on time series.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +2
no code implementations • WS 2019 • Christin Sch{\"a}tzle, Frederik L. Dennig, Michael Blumenschein, Daniel A. Keim, Miriam Butt
This paper presents a significant extension of HistoBankVis, a multilayer visualization system which allows a fast and interactive exploration of complex linguistic data.
1 code implementation • 1 Aug 2019 • David Pomerenke, Frederik L. Dennig, Daniel A. Keim, Johannes Fuchs, Michael Blumenschein
Second, we present a novel technique to reduce the effects by rendering the polylines of the parallel coordinates based on their slope: horizontal lines are rendered with the default width, lines with a steep slope with a thinner line.
Graphics
no code implementations • 19 Dec 2018 • Cagatay Turkay, Nicola Pezzotti, Carsten Binnig, Hendrik Strobelt, Barbara Hammer, Daniel A. Keim, Jean-Daniel Fekete, Themis Palpanas, Yunhai Wang, Florin Rusu
We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.