Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning

In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machine learning and knowledge extraction Jg. 4; H. 4; S. 924 - 953
Hauptverfasser: Saranti, Anna, Hudec, Miroslav, Mináriková, Erika, Takáč, Zdenko, Großschedl, Udo, Koch, Christoph, Pfeifer, Bastian, Angerschmid, Alessa, Holzinger, Andreas
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.12.2022
Schlagworte:
actionable explainable AI
aggregation functions
Artificial intelligence
Classification
continuous XOR-problem
Decision making
Domains
Electronic data processing
Explainable artificial intelligence
Fuzzy algorithms
Fuzzy logic
Fuzzy sets
Fuzzy systems
interpretable machine learning
Linguistics
Machine learning
Methods
Neural networks
Norms
ordinal sums
Parameters
Subject specialists
Austria
ISSN:2504-4990, 2504-4990
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “maybe”, which contains a corresponding quantifiable tendency toward one of these two opposites. Human domain experts are often able to mark any entity, place it in a different class and adjust the position of the slope in the class. Moreover, they can often explain the classification space linguistically—depending on their individual domain experience and previous knowledge. We consider this human-in-the-loop extremely important and call our approach actionable explainable AI. Consequently, the parameters of the functions are adapted to these requirements and the solution is explained to the domain experts accordingly. Specifically, this paper contains three novelties going beyond the state-of-the-art: (1) A novel method for detecting the appropriate parameter range for the averaging function to treat the slope in the “maybe” class, along with a proposal for a better generalisation than the existing solution. (2) the insight that for a given problem, the family of t-norms and t-conorms covering the whole range of nilpotency is suitable because we need a clear “no” or “yes” not only for the borderline cases. Consequently, we adopted the Schweizer–Sklar family of t-norms or t-conorms in ordinal sums. (3) A new fuzzy quasi-dissimilarity function for classification into three classes: Main difference, irrelevant difference and partial difference. We conducted all of our experiments with real-world datasets.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2504-4990
2504-4990
DOI:10.3390/make4040047