English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Explainable Artificial Intelligence (XAI) methods are typically deployed toexplain and debug black-box machine learning models. However, most proposed XAImethods are black-boxes themselves and designed for images. Thus, they rely onvisual interpretability to evaluate and prove explanations. In this work, weapply XAI methods previously used in the image and text-domain on time series.We present a methodology to test and evaluate various XAI methods on timeseries by introducing new verification techniques to incorporate the temporaldimension. We further conduct preliminary experiments to assess the quality ofselected XAI method explanations with various verification methods on a rangeof datasets and inspecting quality metrics on it. We demonstrate that in ourinitial experiments, SHAP works robust for all models, but others likeDeepLIFT, LRP, and Saliency Maps work better with specific architectures.

Towards a Rigorous Evaluation of XAI Methods on Time Series