专题链接

学术看板 当前位置:网站首页 > 专题链接 > 学术看板

机器学习与人工智能讲坛:香港城市大学余雷博士报告通知

作者:统计机器智能与学习实验室 来源:统计机器智能与学习实验室 阅读次数:165日期:2019/05/17

一、主题:Approximate Inference using Simplification of Gaussian Mixture Models
二、主讲人:余雷博士 香港城市大学
三、时间:2019年05月20日上午10:00

四、地点:清水河校区主楼教工之家

五、主持人:计算机科学与工程学院 徐增林教授

六、内容简介:

        Probabilistic modelling and Bayesian inference are principal tools which are widely used in machine learning. An assumption of simple probabilistic models can lead to tractable and efficient computation for inference, but usually it cannot fulfill the requirement of most cases of interest in real world applications. Monte Carlo sampling and variational approximation are the two mainstay approaches for approximate inference. MC sampling approximates the intractable probability distribution with samples, which can be accurate but time consuming. Variational approximation supposes an unknown variational distribution from a tractable family then determines it by solving an optimization problem, which is efficient but tedious mathe matical derivation is required for different models. Considering that finite mixture models are universal approximators for any continuous probability density, we use Gaussian Mixture Models(GMMs) to approximate generic continuous likelihoods in Bayesian inference. We firstly proposed a novel density simplification algorithm that can well preserve the original mixture distribution by directly grouping the base probability densities. Then we show its wide application on recursive Bayesian filtering, KDE mixture reduction, belief propagation and robust Gaussian Process regression.

七、主讲人简介:

        Lei Yu received the B.S. and M.S. degree in Information and Computing Science, and Computer Software and Theory from the Hunan Normal University, Changsha, China, in 2010 and 2013, respectively, and the Ph.D. degree in Computer Science from the City University of Hong Kong, in 2019. From 2011 to 2012, she was a visiting student in Department of Mathematics from Zhejiang University. From 2012 to 2013, she was an intern in Institute of Software Chinese Academy of Sciences (ISCAS). She is now working as a Research Associate in City University of Hong Kong.

八、主办单位:计算机科学与工程学院(网络空间安全学院)

  承办单位:统计机器智能与学习实验室(SMILE Lab)