Machine Learning~(ML) has provided promising results in recent years across different applications and domains. However, in many cases, qualities such as reliability or even safety need to be ensured. To this end, one important aspect is to determine whether or not ML components are deployed in situations that are appropriate for their application scope. For components whose environments are open and variable, for instance those found in autonomous vehicles, it is therefore important to monitor their operational situation to determine its distance from the ML components' trained scope. If that distance is deemed too great, the application may choose to consider the ML component outcome unreliable and switch to alternatives, e.g. using human operator input instead. SafeML is a model-agnostic approach for performing such monitoring, using distance measures based on statistical testing of the training and operational datasets. Limitations in setting SafeML up properly include the lack of a systematic approach for determining, for a given application, how many operational samples are needed to yield reliable distance information as well as to determine an appropriate distance threshold. In this work, we address these limitations by providing a practical approach and demonstrate its use in a well known traffic sign recognition problem, and on an example using the CARLA open-source automotive simulator.
翻译:近年来,机器学习~(ML)在不同应用和领域提供了令人鼓舞的结果,但在许多情况下,需要确保可靠性或甚至安全性等质量,为此,一个重要方面是确定在适合其应用范围的情况下是否部署 ML 组件;对于环境开放且可变的部件,如在自主车辆中发现的部件,因此必须监测其运行状况,以确定其与ML 组件培训范围之间的距离;如果这种距离被认为太远,应用可以选择考虑ML 部件的结果不可靠,转而采用替代方法,例如使用人操作器输入;安全ML 是进行这种监测的示范性、不可接受性方法,采用基于培训和操作数据集统计测试的远程措施; 建立安全ML 的局限性适当包括缺乏系统的方法,无法为特定应用确定需要多少操作样品来生成可靠的远程信息,以及确定适当的距离阈值; 在这项工作中,我们通过提供实用的方法来解决这些局限性,并展示其在众所周知的交通标志识别问题中的用途,以及使用开放汽车的示例。