报告时间：2026年1月28日（周三）15：00-17：00
会议地点：崇德楼422室
报告（一）
报告题目：使用分维微积分和分数阶微积分的更智慧的机器学习
主讲嘉宾：陈阳泉（Prof. YangQuan Chen）
内容简介：In this talk, I will first discuss the meaning of being smart. Then I will argue that machine learning (ML) is not smart yet. After reviewing the roughness nature of the ML loss landscape, I will show that ML is a rough business. After re-iterating the importance of the triangle of “Complexity (C)” – “Inverse Power Law (IPL) – “fractional calculus (FC)”, I explain the three tails (laws): exponential law (EL), stretched exponential law (SEL), and IPL and the corresponding generating relaxation equations of integer order calculus, fractal calculus and fractional calculus. We finally introduce our recent work towards smarter ML using the concept of roughness quantification. The roughness-informed ML is shown to be a smart ML idea.
专家简介：Prof. YangQuan Chen is with the Dept. of Mechanical and Aerospace Engineering at the University of California Merced. He received his B.S. from the University of Science and Technology of Beijing, M.S. from Beijing Institute of Technology, and Ph.D. from Nanyang Technological University Singapore. His research interests include smart mechatronics for sustainability, smart control engineering via digital twins, small multi-UAV based cooperative multi-spectral "personal remote sensing", applied fractional calculus in complex system controls, modeling, signal processing, and machine learning, distributed measurement and control of distributed parameter systems with mobile actuator and sensor networks. He authored many papers, editorials, patents, research monographs and textbooks. His Google Scholar H index = 107 with total citations 61936 and H-10 index 700. His latest books with CRC Press are "Fractional Calculus for Skeptics (1), (11)".
报告（二）
报告题目：具有记忆特性随机网络系统的稳定性分析与控制
主讲嘉宾：于永光
内容简介：本报告针对具有记忆特性的随机网络系统的定性分析和控制进行研究。首先借助构建迭代序列的方法，证明了随机噪声影响下的 Caputo 型分数阶系统解的存在和唯一性。进而给出了在随机噪声影响下的 Caputo 型分数阶网络系统在均方意义下实现渐进稳定的充分条件。同时，对于分数布朗运动驱动的随机网络系统，建立了实现均方渐进稳定的充分条件。并探讨了分数布朗运动驱动的随机网络系统的最优控制问题。
专家简介：于永光，北京交通大学数学与统计学院院长，二级教授、博士生导师，北京市青年教学名师。主要从事记忆特性多尺度系统建模、复杂网络智能控制和分数阶微分方程等方向的研究。主持和参与了国家自然科学基金和国家重点研发计划任务等多个国家级项目。在Automatica，IEEE Transactions on Automatic control等非线性控制领域权威期刊上共发表学术论文200余篇，连续11年入选爱思唯尔中国高被引学者，进入斯坦福大学全球前2%顶尖科学家以及全球学者库“全球顶尖前10万科学家”。曾获北京市科学技术奖自然科学奖二等奖和中国自动化学会自然科学二等奖、国家级一流本科课程、宝钢优秀教师奖、北京市青年教学名师和北京市教学成果一等奖等荣誉和奖励。
欢迎广大师生参会交流！
