研究生课《Machine Learning》、《Pattern Recognition》教学通知(二)
作者:blj 发布日期:2016-01-04 浏览次数:

各选修该课程的同学:
教学安排1:
时间:1月4日下午15:30
地点:健B102
课程负责人:陈胜勇 教授,浙江工业大学
助课:张剑华博士,浙江工业大学
报告主题:计算机视觉在结构健康监测中的应用研究
报告人:叶肖伟 博士、博士生导师,浙江大学求是青年学者
报告内容:近年来,随着我国土木和交通基础设施的蓬勃发展,建造了大量的大型工程结构(千米级跨度的索承桥梁、500米级的高耸结构、超长路径的跨地区高速铁路、超深基坑的城市地下轨道交通等),如何保证这些大型土木和交通基础设施在建设和运营过程中的安全性已经成为工程界和学术界持续关注的热点问题。结构健康监测是土木工程领域新兴的一门交叉学科,其融合了传感、通讯、计算机、大数据管理、结构安全评价等众多领域的科学进展和先进技术,通过对结构关键截面和构件进行全寿命期实时监测,进而对结构的安全性、可靠性、耐久性等性能进行全方位的评估,为工程管理人员提供及时有效的信息用于制定决策。本报告主要介绍一种基于计算机视觉的非接触式结构健康监测技术,针对传统结构健康监测系统中存在的弊端,比如传感器和线缆布设困难、干扰交通等,提出了基于计算机视觉的非接触式桥梁结构安全监测和状态评估理论,发展了基于模板匹配算法的多点结构动态位移计算方法,利用多点结构位移时程信号识别结构动力特性,结合材料力学相关公式获得拉索索力,通过大量实内实验研究验证了方法的可行性。

教学安排2:
时间:1月11日下午15:30
地点:健B102
课程负责人:陈胜勇 教授,浙江工业大学
助课:张剑华博士,浙江工业大学
报告人:沈春华澳大利亚阿德雷德大学教授
报告内容:In this talk, I will give a brief overview of what I have been doing in terms of deep learning; and then mainly focus on two deep structured learning methods. Structured output learning concerns the problem of predicting multiple variables that have dependency, with Conditional random field (CRF) as a typical example. It shows great promise in tasks like semantic image segmentation.  Recently, there is mounting evidence that features from deep convolutional neural networks (CNN) set new records for various vision applications. Here I show how we can combine CRFs with deep CNNs to predict complex labels while considering the dependencies between the output variables.The first application is to learn depth from single monocular images. Compared with depth estimation using multiple images such as stereo depth perception, depth from monocular images is much more challenging. We propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework, termed Deep Convolutional Neural Fields. For the second application, we proffer a new, efficient deep structured model learning scheme, in which we show how deep Convolutional Neural Networks (CNNs) can be used to estimate the
messages in message passing inference for structured prediction with CRFs. With such CNN message estimators, we obviate the need to learn or evaluate potential functions for message calculation. This confers significant efficiency for learning, since otherwise when performing structured learning for a CRF with CNN potentials it is necessary to undertake expensive inference for every stochastic gradient iteration. We also demonstrate that it yields results that are competitive with the state-of-the-art in semantic segmentation for the PASCAL VOC 2012 dataset. 
注:
Machine Learning(16学时):1月4日(选修),1月11日(选修)
Pattern Recognition(32学时):1月4日(选修),1月11日(选修)

以上请各班长及同学相互传达和通知,有问题及时联系我,务必提前10分钟到场以备上课,因课程冲突请假等请联系张剑华老师18957157559或者600 13605813989。预祝大家学习愉快,收获多多!