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 models have achieved remarkable success in different areas ofmachine learning over the past decade; however, the size and complexity ofthese models make them difficult to understand. In an effort to make them moreinterpretable, several recent works focus on explaining parts of a deep neuralnetwork through human-interpretable, semantic attributes. However, it may beimpossible to completely explain complex models using only semantic attributes.In this work, we propose to augment these attributes with a small set ofuninterpretable features. Specifically, we develop a novel explanationframework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) thatdecomposes a model's prediction into two parts: one that is explainable througha linear combination of the semantic attributes, and another that is dependenton the set of uninterpretable features. By identifying the latter, we are ableto analyze the "unexplained" portion of the model, obtaining insights into theinformation used by the model. We show that the set of unlabelled features cangeneralize to multiple models trained with the same feature space and compareour work to two popular attribute-oriented methods, Interpretable BasisDecomposition and Concept Bottleneck, and discuss the additional insights ELUDEprovides.

ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features