澳大利亚西悉尼大学傅周宇博士报告会的通知
时间： 2月19日上午10：30--11:30
地点：第二教学楼南楼228室（自动化学院二楼会议室）
报告题目（TITLE）：Feature Optimisation forSupport Vector Classifier Learning基于支持向量机的特征优化
欢迎老师和研究生参加！
报告摘要（ABSTRACT）：
In this talk, I'll discuss the issue offeature optimisation for supervised learning with the support vectorclassifiers (SVM). The key to this problem is how to effectively associateclassifier learning with feature optimisation. I then present aformulation which involves the use of only a single optimisation problem forsolving both feature and classifier variables. Under some weakassumptions, we can show that the objective function of the optimisationproblem is differentiable and thus can be efficiently solved by gradientdescent. Finally I'll show two applications of the proposed framework onmultiple instance learning and audio classification respectively.
在本报告中，我将讲述基于支持向量机分类器的特征优化问题。问题的关键在于如何将分类器学习和特征学习这两个问题有机结合起来。我提出一个基于优化的方法，只需要求解一个优化问题，就可以得到最优的分类器和特征参数。虽然该优化问题的目标函数形式较复杂，我们发现其是可导的并可用梯度下降法求解。最后我再举两个该方法在多示例学习和音频分类领域的应用。
报告人简介（BIOGRAPHY）：
Zhouyu Fu is a lecturer at the School of Computing, Engineeringand Mathematics?of University of Western Sydney (UWS). Before joining UWS in 2012,he had been a research fellow at the Gippsland School of Information Technology of Monash University since 2012. He didhis PhD at the Australian National University and obtained hisdoctoral degree in Information Engineering in October 2009. He was alsoaffiliated with and sponsored by National ICT Australia during his PhD studies at ANU. Heobtained his master's degree in Pattern Recognition and Intelligent Systemsfrom the National Lab of Pattern Recognition, Institute of Automation, theChinese Academy of Sciences and bachelor's degree in Information Engineeringfrom Zhejiang University in China.
Zhouyu's research interests are mainly in machine learning and patternrecognition, focusing on supervised learning techniques with applications tocomputer vision, image/audio analysis, and multimedia information retrieval.
从2012年初至今，傅周宇博士在澳大利亚西悉尼大学计算机工程和数学学院担任讲师职位。在2009至2011年间，他在莫纳什大学从事博士后研究员。他于2001年在浙江大学信息与电子系获得学士学位，2004年在中国科学院自动化研究所获得硕士学位，2009年获得澳大利亚国立大学博士学位。他的研究兴趣主要在机器学习，模式识别，特别是监督学习在计算机视觉，图像处理和多媒体领域的应用。