5 papers
Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan +2
Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibi…
Improving Explanations: Applying the Feature Understandability Scale for Cost-Sensitive Feature Selection
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan +2
With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniq…
SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data
Mingxing Zhang, Nicola Rossberg, Simone Innocente +5
In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly…
The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan +2
As artificial intelligence becomes increasingly pervasive and powerful, the ability to audit AI-based systems is growing in importance. However, explainability for artificial intel…
SATfeatPy -- A Python-based Feature Extraction System for Satisfiability
Benjamin Provan-Bessell, Marco Dalla, Andrea Visentin +1
Feature extraction is a fundamental task in the application of machine learning methods to SAT solving. It is used in algorithm selection and configuration for solver portfolios an…