Beneficial and harmful explanatory machine learning

Abstract

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.

Generating contrastive explanations for inductive logic programming based on a near miss approach

“…Instead of the use of a cover story, a more realistic setting should be investigated as a next step. Similar to an experiment in the context of explaining the choice of moves in a strategy game (Ai et al 2021), an explanation interface can be added to the learned models. Then, it can be assessed whether participants getting the explanation considered most helpful by the system show better performance than participants getting another explanation.…”

Inductive logic programming at 30

“…Explainability Explainability is one of the claimed advantages of a symbolic representation. Recent work Muggleton et al (2018b) and Ai et al (2020) evaluates the comprehensibility of ILP hypotheses using Michie's Michie (1988) framework of ultra-strong machine learning, where a learned hypothesis is expected to not only be accurate but to also demonstrably improve the performance of a human being provided with the learned hypothesis. Muggleton et al (2018b) empirically demonstrate improved human understanding directly through learned hypotheses.…”

“…Muggleton et al (2018b) empirically demonstrate improved human understanding directly through learned hypotheses. However, given the demonstration of both beneficial and harmful effects of explainability (Ai et al, 2020) more work is required to better understand the conditions under which this can be achieved, especially given the rise of PI.…”

Humanzentrierte Künstliche Intelligenz: Erklärendes interaktives maschinelles Lernen für Effizienzsteigerung von Parametrieraufgaben

“…Um komplexe Zusammenhänge zu kommunizieren sind häufig verbale oder andere Arten symbolischer Erklärungen notwendig (Schmid, 2021), im Zweifel unter Verwendung eines mehrschrittigen Dialogs (Finzel et al, 2021). Generell ist aber zu beachten, dass Erklärungen nicht zu komplex sein sollten, um die kognitive Belastung gering zu halten (Ai et al, 2021).…”

“…Den Kern der Verantwortungsethik für KI bildet ein nutzer-und mitarbeiterzentriertes Denken und Handeln auf allen Ebenen. KI als neues Werkzeug soll den Menschen unterstützen und ihm dienen (Ai et al, 2021). Häufig besteht Skepsis gegenüber KI.…”