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

Deep Learning has become a very valuable tool in different fields, and no onedoubts the learning capacity of these models. Nevertheless, since Deep Learningmodels are often seen as black boxes due to their lack of interpretability,there is a general mistrust in their decision-making process. To find a balancebetween effectiveness and interpretability, Explainable Artificial Intelligence(XAI) is gaining popularity in recent years, and some of the methods withinthis area are used to generate counterfactual explanations. The process ofgenerating these explanations generally consists of solving an optimizationproblem for each input to be explained, which is unfeasible when real-timefeedback is needed. To speed up this process, some methods have made use ofautoencoders to generate instant counterfactual explanations. Recently, amethod called Deep Guided Counterfactual Explanations (DGCEx) has beenproposed, which trains an autoencoder attached to a classification model, inorder to generate straightforward counterfactual explanations. However, thismethod does not ensure that the generated counterfactual instances are close tothe data manifold, so unrealistic counterfactual instances may be generated. Toovercome this issue, this paper presents Distribution Aware Deep GuidedCounterfactual Explanations (DA-DGCEx), which adds a term to the DGCEx costfunction that penalizes out of distribution counterfactual instances.

DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss