Beneficial and Harmful Explanatory Machine Learning

TL;DR

This paper explores how machine learned explanations can both benefit and harm human learning, proposing a framework to identify when explanations are helpful or detrimental based on cognitive science principles.

Contribution

It introduces a framework for assessing the beneficial or harmful effects of machine explanations on human learning, supported by empirical human trials.

Findings

Explanations within a cognitive window improve human performance.

Explanations outside the cognitive window impair human learning.

Empirical evidence supports the proposed framework.

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.