Search Results for author:
Found 19 papers, 5 papers with code
generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation
Large language models (LLMs) are widely deployed in various downstream tasks, e. g., auto-completion, aided writing, or chat-based text generation.
Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges
We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges.
Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions
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.
Visual Explanations with Attributions and Counterfactuals on Time Series Classification
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.
A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
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
How to Enable Uncertainty Estimation in Proximal Policy Optimization
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)
BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning
Robustness to adversarial perturbations has been explored in many areas of computer vision.
ViNNPruner: Visual Interactive Pruning for Deep Learning
In many cases, such large networks are not deployable on particular hardware and need to be reduced in size.
CorpusVis: Visual Analysis of Digital Sheet Music Collections
Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information.
Time Series Model Attribution Visualizations as Explanations
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.
TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models
Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances.
Video-based Analysis of Soccer Matches
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.
An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks
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
MultiSegVA: Using Visual Analytics to Segment Biologging Time Series on Multiple Scales
To close this gap, we present our MultiSegVA platform for interactively defining segmentation techniques and parameters on multiple temporal scales.
Towards a Rigorous Evaluation of XAI Methods on Time Series
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
Visualizing Linguistic Change as Dimension Interactions
This paper presents a significant extension of HistoBankVis, a multilayer visualization system which allows a fast and interactive exploration of complex linguistic data.
Slope-Dependent Rendering of Parallel Coordinates to Reduce Density Distortion and Ghost Clusters
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
Progressive Data Science: Potential and Challenges
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.
