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.…
| Document Type: | Conference Proceeding |
|---|---|
| Conference Type: | Konferenzartikel |
| Zitierlink: | https://opus.hs-offenburg.de/4456 | Bibliografische Angaben |
| Title (English): | An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks |
| Conference: | Pre-registration workshop NeurIPS (2020), Vancouver, Canada |
| Author: | Udo Schlegel, Daniela OelkeStaff MemberORCiDGND, Daniel A. Keim, Mennatallah El-Assady |
| Year of Publication: | 2021 |
| Date of first Publication: | 2020/12/08 |
| Page Number: | 7 |
| First Page: | 1 |
| Last Page: | 7 |
| Parent Title (English): | [NeurIPS 2020 Workshops] |
| URL: | https://deepai.org/publication/an-empirical-study-of-explainable-ai-techniques-on-deep-learning-models-for-time-series-tasks |
| Language: | English | Inhaltliche Informationen |
| Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
| Collections of the Offenburg University: | Bibliografie | Formale Angaben |
| Open Access: | Open Access |
| Licence (German): |  Urheberrechtlich geschützt |
| ArXiv Id: | http://arxiv.org/abs/2012.04344 |