loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Dominique Mercier 1 ; 2 ; Jwalin Bhatt 2 ; Andreas Dengel 1 ; 2 and Sheraz Ahmed 1

Affiliations: 1 German Research Center for Artificial Intelligence GmbH (DFKI), Kaiserslautern, Germany ; 2 Technical University Kaiserslautern (TUK), Kaiserslautern, Germany

Keyword(s): Deep Learning, Time Series, Interpretability, Attribution, Benchmarking, Convolutional Neural Network, Artificial Intelligence, Survey.

Abstract: In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However, due to the lack of transparency the use of these networks is hampered in the areas with safety critical areas. In safety-critical areas, this is necessary by law. Recently several methods have been proposed to uncover this black box by providing interpreation of predictions made by these models. The paper focuses on time series analysis and benchmark several state-of-the-art attribution methods which compute explanations for convolutional classifiers. The presented experiments involve gradient-based and perturbation-based attribution methods. A detailed analysis shows that perturbation-based approaches are superior concerning the Sensitivity and occlusion game. These methods tend to produce explanations with higher continuity. Contrarily, the gradient-based techniques are superb in runtime and Infidelity. In addition, a validation the dependence of the methods on the trained model, feasible application domains, and individual characteristics is attached. The findings accentuate that choosing the best-suited attribution method is strongly correlated with the desired use case. Neither category of attribution methods nor a single approach has shown outstanding performance across all aspects. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 98.80.143.34

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Mercier, D.; Bhatt, J.; Dengel, A. and Ahmed, S. (2022). Time to Focus: A Comprehensive Benchmark using Time Series Attribution Methods. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 562-573. DOI: 10.5220/0010904400003116

@conference{icaart22,
author={Dominique Mercier. and Jwalin Bhatt. and Andreas Dengel. and Sheraz Ahmed.},
title={Time to Focus: A Comprehensive Benchmark using Time Series Attribution Methods},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2022},
pages={562-573},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010904400003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Time to Focus: A Comprehensive Benchmark using Time Series Attribution Methods
SN - 978-989-758-547-0
IS - 2184-433X
AU - Mercier, D.
AU - Bhatt, J.
AU - Dengel, A.
AU - Ahmed, S.
PY - 2022
SP - 562
EP - 573
DO - 10.5220/0010904400003116
PB - SciTePress