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

To explain the decision of any model, we extend the notion of probabilisticSufficient Explanations (P-SE). For each instance, this approach selects theminimal subset of features that is sufficient to yield the same prediction withhigh probability, while removing other features. The crux of P-SE is to computethe conditional probability of maintaining the same prediction. Therefore, weintroduce an accurate and fast estimator of this probability via random Forestsfor any data $(\boldsymbol{X}, Y)$ and show its efficiency through atheoretical analysis of its consistency. As a consequence, we extend the P-SEto regression problems. In addition, we deal with non-discrete features,without learning the distribution of $\boldsymbol{X}$ nor having the model formaking predictions. Finally, we introduce local rule-based explanations forregression/classification based on the P-SE and compare our approaches w.r.tother explainable AI methods. These methods are available as a Python packageat \url{www.github.com/salimamoukou/acv00}.

Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models