Title: 第20届CCF全国嵌入式系统大会(CCF ESTC 2022)活动流程<br> Time： 08:30-19:00, October9 Sunday,2022<br> Location: <br> Lecturer：魏同权、邹桉、张凯龙、邓庆绪、董云卫、陈仪香、周俊龙

报告题目：Temporal Satisfiability Modulo Theories报告时间：11月2日 xx:00-xx：xx线下报告地点：理科大楼B1002腾讯会议号：主持人：李建文报告摘要：Checking temporal satisfiability (or validity) is a fundamental problem to make formal verification scale up with compositional reasoning. In this talk, we focus on LTL satisfiability modulo theories, which generalizes the satisfiability problem for LTL to the first-order case with respect to some background theories. Compositional reasoning takes into account both synchronous and asynchronous int

报告题目：Data Science for Deep Learning报告时间：10月20日 11:00-12：30线下报告地点：理科大楼B1002腾讯会议号：980181758主持人：程鹏报告摘要：In recent years, deep learning (DL) has significantly penetrated and has been widely adopted in various fields of application, including facial recognition, strategy games (AlphaGo and Texas holdem) and question answering. However, the effectiveness of the models and efficiency of the training process strongly depend on how well the associated data is managed. It is very challenging to train an ef

报告题目：Reachability Analysis of Learning-Enabled Cyber-Physical Systems报告时间：12月29日 09:00线下报告地点：理科大楼B002腾讯会议号：763-614-103主持人：张民教授报告摘要：Neural networks have been increasingly used as the central decision makers in a variety of tasks. However, the use of neural-network controllers also gives rise to new challenges on verifying the correctness of the resulting closed-loop control systems especially in safety-critical settings. This talk focuses on computing the reachable sets of Cyber-Physical Systems

报告一题目：Deductive Database Abduction：Journey from Past to Future报告时间：12月15日14：00报告地点：数学馆201腾讯会议号：650-854-178主持人：陈仪香 教授报告摘要：In this talk, we will cover the following 3 areas. The first is to share the some of the Fifth Generation Computer research work done in 1980-1990s on Deductive Database and Abduction. The second will cover industry use cases integrating deductive database system and constraint configurator system with big data system. Lastly, we will explore and discuss what are future poten

报告题目：可信AI业界洞察与华为AI可靠性技术布局报告时间：12月13日14：50报告地点：理科大楼B002主持人：张民 教授报告摘要：近年来人工智能技术取得了巨大的成功。然而这些AI系统仍不够完美，存在不同场景下可靠性隐患难以发现，缺乏全面集成的系统级测试，缺乏有效的诊断升级手段等问题。业界Google微软IBM等公司纷纷在可信AI的鲁棒性训练，测试验证，运行维护等方面投入和布局。华为可信院也分别在AI系统开发态的鲁棒性技术，测试态的测试验证手段和运行态的监控技术进行了相应的项目布局。报告人简介：法国里昂国立应用科学学院计算机博士，现任华为2012可信院RAMS实验室可信AI研究员，主要负责自动驾驶感知安全可信技术研究。