学术报告1

题目：Evolutionary neural architecture search: Knowledge transfer,privacy
preservation and adversarial robustness

报告人：Yaochu Jin、Fellow of the European Academy of Sciences 

时间：5月16日上午

地点：信息学院402学术报告厅

摘要：This talk presents some recent advances in evolutionary neural architecture search. We present methods for improving the computational efficiency of neural architecture search with the help of surrogate modeling and knowledge transfer, and introduce neural architecture search methods that can preserve data privacy. Finally, we discuss ideas of improving the adversarial robustness of neural network models to achieve robustness by design.

报告人简介：Yaochu Jin is an Alexander von Humboldt Professor for Artificial Intelligence endowed by the German Federal Ministry of Education and Research, with the Faculty of Technology, Bielefeld University, Germany. He is also a Distinguished Chair, Professor in Computational Intelligence, Department of Computer Science, University of Surrey, Guildford, U.K. He was a “Finland Distinguished Professor” of University of Jyväskylä, Finland, “Changjiang Distinguished Visiting Professor”, Northeastern University, China, and “Distinguished Visiting Scholar”, University of Technology Sydney, Australia. His main research interests include multi-objective and data-driven evolutionary optimization, evolutionary multi-objective learning, trustworthy AI, and evolutionary developmental AI.  Prof Jin is presently the President-Elect of the IEEE Computational Intelligence Society and the Editor-in-Chief of Complex & Intelligent Systems. He was named by the Web of Science as “a Highly Cited Researcher” from 2019 to 2022 consecutively. He is a Member of Academia Europaea and Fellow of IEEE.

学术报告2

题目：非平衡数据流分类方法

报告人：郭一楠 中国矿业大学教授、博导

时间：5月16日上午

地点：信息学院402学术报告厅

摘要：针对广泛存在于故障识别、医疗诊断、欺诈检测等领域中的非平衡数据，分别提出基于流形距离的新型过采样技术和样本数量自适应调整方法，以及基于流形聚类的双层进化集成分类框架，为非平衡数据分类提供更加鲁棒和强泛化能力的解决途径；进而，针对有限标记的非平衡数据，构建了加权迁移极限学习分类器，通过合理迁移已有标记数据下获得的分类模型，提高有限标记数据的分类性能；进一步，面向存在概念漂移的非平衡数据流，提出集成分类器的动态生成方法和自适应近邻重采样策略，生成符合新概念的少数类实例,并自适应构建最佳候选分类器组合。上述理论框架和方法被进一步应用于解决工业故障诊断和井下微震信号识别。

报告人简介：郭一楠，中国矿业大学教授、博士生导师，中国矿业大学人工智能研究院智慧医疗中心副主任，清华大学、美国明尼苏达大学、英国伯明翰大学访问学者；中国煤炭青年科技奖获得者，江苏省六大高峰人才，江苏省青蓝工程骨干教师，江苏省工信厅特聘专家。中国人工智能学会高级会员、中国仿真学会智能仿真优化与调度专委会秘书长、中国自动化学会大数据专委会和智慧矿山专委会委员，中国人工智能学会智慧医疗专委会委员。International Journal of Coal Science & Technology和和International Journal of Bio-Inspired Computation编委、Swarm and Evolutionary Computation、Sensors等期刊客座编委。主要从事群智优化与智能控制、智能数据解析与影像理解、数字孪生与平行理论，以及相关方法在有限资源调度、复杂装备控制、主动健康、矿山智能化等领域的应用研究。主持/参与国家重点研发计划、国家973计划、国家863计划、国家自然科学基金项目和校企产学研合作项目等科研项目30余项，以第一作者/通讯作者在IEEE/IFAC汇刊IEEE Transactions on Evolutionary Computation、IEEE Transactions on Neural Network and Learning System、IEEE Transactions on Cybernetics、IEEE-ASME Transactions on Mechatronics、IEEE Transactions on Emerging Topics in Computational Intelligence、Control Engineering Practice等权威期刊上发表SCI论文40余篇，2篇论文入选ESI高被引论文，2篇论文分别入选中国百篇最具影响国内学术论文和中国精品科技期刊顶尖学术F5000论文，授权国家发明专利19项，软件著作权14项。曾获教育部科技进步奖二等奖、江苏省科学技术奖二等奖、煤炭部科技进步奖二等奖、吴文俊人工智能科学技术奖二等奖、中国电子学会电子信息科学技术奖二等奖等科研奖励12项。

信息科学技术学院（微电子学院）

                                                        2023.5.8