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

From self-driving vehicles and back-flipping robots to virtual assistants whobook our next appointment at the hair salon or at that restaurant for dinner -machine learning systems are becoming increasingly ubiquitous. The main reasonfor this is that these methods boast remarkable predictive capabilities.However, most of these models remain black boxes, meaning that it is verychallenging for humans to follow and understand their intricate inner workings.Consequently, interpretability has suffered under this ever-increasingcomplexity of machine learning models. Especially with regards to newregulations, such as the General Data Protection Regulation (GDPR), thenecessity for plausibility and verifiability of predictions made by these blackboxes is indispensable. Driven by the needs of industry and practice, theresearch community has recognised this interpretability problem and focussed ondeveloping a growing number of so-called explanation methods over the past fewyears. These methods explain individual predictions made by black box machinelearning models and help to recover some of the lost interpretability. With theproliferation of these explanation methods, it is, however, often unclear,which explanation method offers a higher explanation quality, or is generallybetter-suited for the situation at hand. In this thesis, we thus propose anaxiomatic framework, which allows comparing the quality of differentexplanation methods amongst each other. Through experimental validation, wefind that the developed framework is useful to assess the explanation qualityof different explanation methods and reach conclusions that are consistent withindependent research.

Shedding Light on Black Box Machine Learning Algorithms: Development of  an Axiomatic Framework to Assess the Quality of Methods that Explain  Individual Predictions