Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 1 of 1
Back to Result List

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. 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 applyDecision 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.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Udo Schlegel, Daniela Oelke, Daniel A. Keim, Mennatallah El-Assady
Year of Publication:2020
Page Number:7
Language:English
Document Type:Conference Proceeding
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2021/01/08
Licence (German):License LogoEs gilt das UrhG
Note:
Pre-registration workshop NeurIPS (2020), Vancouver, Canada.
URL:https://preregister.science/papers_20neurips/7_paper.pdf
ArXiv Id:http://arxiv.org/abs/2012.04344