报告题目：Flexible and Consistent Face Alignment via Large Deformation Diffeomorphic Metric Mapping and Deep Learning报 告 人：唐晓颖 副研究员（南方科技大学） 报告时间：4月6日9:30 报告地点：南一楼中311会议室主持人：陶文兵 教授Abstract：Face alignment is a prerequisite in many computer vision tasks, such as face recognition, facial expression recognition, face verification, face reconstruction a...

报告题目：基于网络群体智能的智能交通研究 (Networked Collective Intelligence in Intelligent Transportation System)报 告 人：虞文武 教授（东南大学）报告时间：4月2日14：30-15：30办公地点：南一楼中311室主 持 人：曾志刚 教授 内容摘要: In this talk, I will address applications of machine learning techniques to intelligent transportation systems test cases. Intelligent transportation systems cannot be...

报告题目：Principles of Reinforcement Learning报 告 人：Hamid Reza Karimi，意大利米兰理工大学教授报告时间：2021年3月24日（周三）下午16:30报告地点：南一楼中312室报告摘要:This talk is developed to the principles of reinforcement learning (RL) as a framework for solving control tasks, so-called decision problems, by building agents that learn from the environment. Specifically, Markov decision pro...

报告题目：Hierarchical Decentralized Optimization Architecture for Economic Dispatch: A New Approach for Large-Scale Power System报 告 人：Changyun Wen，新加坡南洋理工大学教授报告时间：2021年3月24日（周三）下午15:00-16:00报告地点：南一楼中312室报告摘要:Conventionally, the economic dispatch problem for a large-scale power system is solved in a centralized way. In contrast to such kind of approac...

报告题目：人工智能技术发展与展望报 告 人：潘泉 教授（西北工业大学）报告时间：2021年3月18日 10:30报告地点：南一楼中311室报告摘要：人工智能技术的发展经历了三次大起伏，其理论与方法不断发展的同时，也在各个领域不断得到成功应用。近年来，以深度学习为标志的新一代人工智能技术得到广泛深入的研究，并在模式识别等领域取得巨大成功，使智能技术发展再上一个新的台阶，但是深度学习的可解释性、性能下界、鲁棒性、泛化...

报告题目: Integrated circuit design for deep learning and AI applications报 告 人：Maciej Jerzy Ogorzalek, Jagiellonian University, Poland报告时间：2021年3月10日报告地点：线上报告 Abstract: Integrated circuits are omnipresent. We not only use mobile phones, personal computers but we are surrounded by systems whose operation highly depends on advances sensors, processing systems, controllers etc...

报告题目：Dealing with concept drift in stream data mining报 告 人：Leszek Rutkowski, Czestochowa University of Technology, Poland报告时间：2021年3月10日报告地点：线上报告Abstract: This lecture presents an overview of techniques to deal with concept drift in stream data mining, and moreover, describes original concepts developed by the author to solve classification and regression problems in a...

报告题目: Cognitive biases in human centric decision making and control报 告 人：Janusz Kacprzyk, 波兰科学院报告时间：2021年3月10日报告地点：线上报告 Abstract: We deal with the broadly perceived decision making and control in a human centric context, that is, when the human being is a key elements, and his/her judgments, assessments and evaluations play an important role. The solutions obtained...

报告题目: Searching for fingerprints of brain activity报 告 人：Włodzisław Duch, Nicolaus Copernicus University, Poland报告时间：2021年3月10日报告地点：线上报告 Abstract: In recent years great progress in methods of brain activity measurement, analysis of neuroimaging and electrophysiological data enabled understanding of some brain processes. Identifying patterns of EEG/MEG, ECoG or fMRI sig...

报告题目: Modelling the magnetic and magneto-mechanical properties of materials for bio-medical and mechatronics applications报 告 人：Roman Szewczyk, Warsaw University of Technology, Poland报告时间：2021年3月10日报告地点：线上报告 Abstract: This talk will introduce approaches to modelling the magnetic and magneto-mechanical properties of materials for bio-medical and mechatronics applicationsB...