报告题目：Collaborative Learning and Optimisation
报 告 人：秦凯 副教授 （青年千人）
单 位：Swinburne University of Technology, Melbourne, Australia
Learning and optimisation are two essential tasks that artificial intelligence aims at addressing, where numerous techniques have been developed for these two purposes separately. In fact, learning and optimisation are closely related. On the one hand, learning can be formulated as a model-centric or data-centric optimisation problem, and accordingly solved by optimisation techniques. On the other hand, optimisation can be regarded as an adaptive learning process, and thus tackled via learning approaches. This talk will discuss collaborations between learning and optimisation from the aspects of optimisation for learning, learning for optimisation and learning plus optimisation, and describe some recent works as case studies in each of these three aspects.
Kai Qin is an Associate Professor at Swinburne University of Technology, Melbourne, Australia, currently serving as the Program Leader on “Data Analytics” in Swinburne Data Science Research Institute (DSRI), the Leader of DSRI’s Machine Learning and Intelligent Optimisation Research Group, the Director of Swinburne’s Intelligent Data Analytics Lab, and the Course Director of Swinburne’s Master of Data Science Program. Before joining Swinburne, he worked at the Nanyang Technological University (Singapore), the University of Waterloo (Canada), INRIA (France) and RMIT University (Australia). His major research interests include evolutionary computation, machine learning, intelligent data analytics (incl. image, text and time-series data), computer vision, remote sensing, GPU computing and services computing. He won the 2012 IEEE Transactions on Evolutionary Computation Outstanding Paper Award and the Overall Best Paper Award at the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES 2014). One of his conference papers was nominated for the best paper award at the 2012 Genetic and Evolutionary Computation Conference (GECCO 2012). He is currently co-chairing the IEEE Computational Intelligence Society (CIS) Task Forces on “Collaborative Learning and Optimization” and “Multitask Learning and Multitask Optimization”, and also serving as the Vice-Chair of the IEEE CIS Technical Committee on Neural Networks.