TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Schlegel, Udo
A1  - Oelke, Daniela
A1  - Keim, Daniel A.
A1  - El-Assady, Mennatallah
T1  - An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks
T2  - [NeurIPS 2020 Workshops]
N2  - Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.
Y1  - 2021
UR  - https://deepai.org/publication/an-empirical-study-of-explainable-ai-techniques-on-deep-learning-models-for-time-series-tasks
AX  - 2012.04344
SP  - 1
EP  - 7
S1  - 7
ER  -