activity
20172024
most citedShould We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations

11 citations · 30 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2022

How to Enable Uncertainty Estimation in Proximal Policy Optimization

Eugene Bykovets, Yannick Metz, Mennatallah El-Assady +2

While deep reinforcement learning (RL) agents have showcased strong results across many domains, a major concern is their inherent opaqueness and the safety of such systems in real…

cs.LG2022

ViNNPruner: Visual Interactive Pruning for Deep Learning

Udo Schlegel, Samuel Schiegg, Daniel A. Keim

Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size.…

cs.LG2021

Time Series Model Attribution Visualizations as Explanations

Udo Schlegel, Daniel A. Keim

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In ma…

cs.LG20211 cited

TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models

Udo Schlegel, Duy Vo Lam, Daniel A. Keim +1

Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances. However, understanding and de…

cs.LG20204 cited

An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks

Udo Schlegel, Daniela Oelke, Daniel A. Keim +1

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified ou…

cs.LG2019

Towards a Rigorous Evaluation of XAI Methods on Time Series

Udo Schlegel, Hiba Arnout, Mennatallah El-Assady +2

Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes…