Bridging the Gap Between AI and Reality - First International Conference, AISoLA 2023, Crete, Greece, October 23-28, 2023, Proceedings
Bridging the Gap Between AI and Reality - First International Conference, AISoLA 2023, Crete, Greece, October 23-28, 2023, Proceedings
复制标题
弥合人工智能与现实之间的差距 - 第一届国际会议，AISoLA 2023，希腊克里特岛，2023 年 10 月 23-28 日，会议记录
DOI：
10.1007/978-3-031-46002-9_4
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Bensalem S
中科院分区：
文献类型：
--
作者：
Bensalem S
机器学习已经取得了显着的进步，但在安全关键领域自信地利用支持学习的组件仍然面临挑战。在这些挑战中，众所周知，实现安全保障的严格而实用的方式是最突出的挑战之一。在本文中，我们首先讨论了工程和研究的挑战与设计和验证这样的系统。然后，基于现有的工作，实际上不能实现可证明的保证，我们提出了一个两步验证方法，最终实现可证明的统计保证。
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving safety guarantees is one of the most prominent. In this paper, we first discuss the engineering and research challenges associated with the design and verification of such systems. Then, based on the observation that existing works cannot actually achieve provable guarantees, we promote a two-step verification method for the ultimate achievement of provable statistical guarantees.