TY - JOUR TI - Beneficial and harmful explanatory machine learning AU - Ai, Lun AU - Muggleton, Stephen H. AU - Hocquette, Céline AU - Gromowski, Mark AU - Schmid, Ute PY - 2021 JO - Machine learning VL - 110 IS - 4 SP - 695–721 PB - Springer CY - Dordrecht SN - 0885-6125 DO - 10.1007/s10994-020-05941-0 UR - https://fis.uni-bamberg.de/handle/uniba/51179 LA - eng AB - 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. KW - Critical Thinking KW - Instructional Theory KW - Learning Theory KW - Machine Learning KW - Symbolic AI KW - Artificial Intelligence ER -