Kara Combs, Mary Fendley, Trevor Bihl, "A Preliminary Look at Heuristic Analysis for Assessing Artificial Intelligence Explainability," WSEAS Transactions on Computer Research, vol. 8, pp. 61-72, 2020, DOI:10.37394/232018.2020.8.9
Kara Combs, Mary Fendley, Trevor Bihl. A Preliminary Look at Heuristic Analysis for Assessing Artificial Intelligence Explainability.
WSEAS Transactions on Computer Research. 2020;8:61-72. 10.37394/232018.2020.8.9
WSEAS Transactions on Computer Research
Print ISSN: 1991-8755, E-ISSN: 2415-1521
Volume 8, 2020
A Preliminary Look at Heuristic Analysis for Assessing Artificial Intelligence Explainability
Authors: , ,
Abstract: Artificial Intelligence and Machine Learning (AI/ML) models are increasingly criticized for their “black-box” nature. Therefore, eXplainable AI (XAI) approaches to extract human-interpretable decision processes from algorithms have been explored. However, XAI research lacks understanding of algorithmic explainability from a human factors’ perspective. This paper presents a repeatable human factors heuristic analysis for XAI with a demonstration on four decision tree classifier algorithms
Keywords:
Artificial intelligence, classification and regression trees, decision trees, explainable AI, heuristic analysis, machine learning, XAI
Pages: 61-72 WSEAS Transactions on Computer Research, ISSN / E-ISSN: 1991-8755 / 2415-1521, Volume 8, 2020, Art. #9 DOI: 10.37394/232018.2020.8.9
×
Citation Tools