争论机器:人类对做出生命攸关决策的黑匣子AI系统的监督
Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions
摘要:
我们考虑黑盒AI系统的范例,它可以做出对生命至关重要的决定。我们提出了一个“争论机器”框架,将主AI系统与独立训练以执行相同任务的辅助AI系统配对。我们表明,两个系统之间的分歧,没有任何知识的基础系统的设计或操作,是足以任意提高整体决策管道的准确性给予人类监督的分歧。我们在两个应用中演示了该系统:(1)图像分类的说明性示例和(2)大规模真实世界半自动驾驶数据。对于第一个应用程序,我们将此框架应用于图像分类,在ImageNet上将前5名错误从8.0%减少到2.8%。对于第二个应用程序,我们将此框架应用于特斯拉自动驾驶仪,并展示了预测90.4%的系统脱离的能力,这些系统脱离被人类注释者标记为具有挑战性并需要人类监督。
英文摘要:
We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task. We show that disagreement between the two systems, without any knowledge of underlying system design or operation, is sufficient to arbitrarily improve the accuracy of the overall decision pipeline given human supervision over disagreements. We demonstrate this system in two applications: (1) an illustrative example of image classification and (2) on large-scale real-world semi-autonomous driving data. For the first application, we apply this framework to image classification achieving a reduction from 8.0% to 2.8% top-5 error on ImageNet. For the second application, we apply this framework to Tesla Autopilot and demonstrate the ability to predict 90.4% of system disengagements that were labeled by human annotators as challenging and needing human supervision.
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。