arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.00582cs.AIcs.LG
收藏

学习补充人类

Learning to Complement Humans

School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院);Microsoft Research(微软研究院)

Bryan Wilder, Eric Horvitz, Ece Kamar

摘要:

在开放世界中,人工智能的一个新兴愿景是开发能够补充人类感知、诊断和推理任务的系统。到目前为止,旨在补充人们技能的系统已经采用了经过培训的模型,以便在孤立的情况下尽可能准确。我们展示了如何利用端到端的学习策略,通过考虑人和机器的不同能力来优化人机团队的综合性能。我们的目标是将机器学习集中在对人类来说很难的问题实例上,同时识别对机器来说很难的实例并寻求人类对它们的输入。我们在两个现实世界的领域(科学发现和医疗诊断)中证明,通过这些方法建立的人机团队的表现优于机器和人的个人表现。然后我们分析了这种互补性最强的条件,以及哪些训练方法放大了它。总之,我们的工作首次系统地研究了如何训练机器学习系统来补充人类推理。

英文摘要:

A rising vision for AI in the open world centers on the development of systems that can complement humans for perceptual, diagnostic, and reasoning tasks. To date, systems aimed at complementing the skills of people have employed models trained to be as accurate as possible in isolation. We demonstrate how an end-to-end learning strategy can be harnessed to optimize the combined performance of human-machine teams by considering the distinct abilities of people and machines. The goal is to focus machine learning on problem instances that are difficult for humans, while recognizing instances that are difficult for the machine and seeking human input on them. We demonstrate in two real-world domains (scientific discovery and medical diagnosis) that human-machine teams built via these methods outperform the individual performance of machines and people. We then analyze conditions under which this complementarity is strongest, and which training methods amplify it. Taken together, our work provides the first systematic investigation of how machine learning systems can be trained to complement human reasoning.

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。

↑