Beneficial and harmful explanatory machine learning

Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machine learning Jg. 110; H. 4; S. 695 - 721
Hauptverfasser: Ai, Lun, Muggleton, Stephen H., Hocquette, Céline, Gromowski, Mark, Schmid, Ute
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.04.2021
Springer Nature B.V
Schlagworte:
Artificial Intelligence
Computer Science
Context
Control
Human performance
Machine Learning
Mechatronics
Natural Language Processing (NLP)
Robotics
Simulation and Modeling
Special issue on Learning and Reasoning
Comprehensibility
Ultra-strong machine learning
Explainable AI
Inductive logic programming
ISSN:0885-6125, 1573-0565
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine’s involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-6125
1573-0565
DOI:10.1007/s10994-020-05941-0