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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Explainability techniques for data-driven predictive models based onartificial intelligence and machine learning algorithms allow us to betterunderstand the operation of such systems and help to hold them accountable. Newtransparency approaches are developed at breakneck speed, enabling us to peekinside these black boxes and interpret their decisions. Many of thesetechniques are introduced as monolithic tools, giving the impression ofone-size-fits-all and end-to-end algorithms with limited customisability.Nevertheless, such approaches are often composed of multiple interchangeablemodules that need to be tuned to the problem at hand to produce meaningfulexplanations. This paper introduces a collection of hands-on training materials-- slides, video recordings and Jupyter Notebooks -- that provide guidancethrough the process of building and evaluating bespoke modular surrogateexplainers for tabular data. These resources cover the three core buildingblocks of this technique: interpretable representation composition, datasampling and explanation generation.

What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components