arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.13271cs.CY
收藏

论公平与可解释性

On Fairness and Interpretability

Deepak P, Sanil V, Joemon M. Jose

摘要:

道德人工智能涵盖了各种考虑因素。其中,最受欢迎的,公平性和可解释性,在技术追求中仍然很大程度上是不同的。我们讨论和阐明公平性和可解释性之间的差异,在各种维度。此外,我们还开发了两个基于原则的框架,旨在为未来开发道德AI,包括公平性和可解释性方面。首先,公平的可解释性提出在公平领域内实例化可解释性,以开发一种新的道德AI。第二,公平性和可解释性引发了关于将两者的最佳方面结合在一起的审议。我们希望这两个框架将有助于加强关于伦理人工智能新领域的学术讨论,将公平性和可解释性结合在一起。

英文摘要:

Ethical AI spans a gamut of considerations. Among these, the most popular ones, fairness and interpretability, have remained largely distinct in technical pursuits. We discuss and elucidate the differences between fairness and interpretability across a variety of dimensions. Further, we develop two principles-based frameworks towards developing ethical AI for the future that embrace aspects of both fairness and interpretability. First, interpretability for fairness proposes instantiating interpretability within the realm of fairness to develop a new breed of ethical AI. Second, fairness and interpretability initiates deliberations on bringing the best aspects of both together. We hope that these two frameworks will contribute to intensifying scholarly discussions on new frontiers of ethical AI that brings together fairness and interpretability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑