Beneficial and harmful explanatory machine learning
Beneficial and harmful explanatory machine learning
复制标题
DOI：
10.1007/s10994-020-05941-0
复制
发表时间：
2021-03-11
期刊：
影响因子：
7.5
通讯作者：
Schmid, Ute
中科院分区：
文献类型：
--
作者：
Ai, Lun;Muggleton, Stephen H.;Schmid, Ute
鉴于最近深度学习在人工智能领域的成功，人们对机器学习理论的作用和解释的需求越来越感兴趣。在这种情况下，一个明显的概念是Michie对超强机器学习（USML）的定义。USML通过向人类提供任务执行的符号机器学习理论后，人类任务绩效的可测量增长来证明。最近的一篇论文展示了机器学习逻辑理论对分类任务的有益影响，但据我们所知，目前还没有研究过机器在学习过程中对人类理解的潜在危害。本文研究了机器学习理论在简单的两人博弈背景下的解释效果，并基于认知科学文献提出了一个识别机器解释危害性的框架。该方法涉及一个由两个可量化界限组成的认知窗口，并得到从人体试验中收集的经验证据的支持。我们的定量和定性结果表明，在满足认知窗口的符号机器学习理论的辅助下，人类学习取得了比人类自我学习更高的性能。结果还表明，在符号机器学习理论的帮助下，人类学习不能满足这个窗口，导致的表现明显比没有帮助的人类学习更差。
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.