加入收藏夹
联系我们
关于本站
个人主页
西电导航
西安电子科技大学
    当前位置:首页>>学术讲座
Graph models for high dimensional data and deep neural networks for images with medical applications
时间:2019-09-26 17:02    点击:   所属单位:人工智能学院
讲座名称 Graph models for high dimensional data and deep neural networks for images with medical applications
讲座时间 2019-09-27 16:00:00
讲座地点 西电北校区主楼II区424会议室
讲座人 Xue-Cheng Tai
讲座人介绍
 Xue-Cheng Tai, Department of Mathematics, Hong Kong Baptist University. 
讲座内容
In this talk, I will present some new research work in several directions. First, we will show some graph models with applications to high dimensional data clustering. Especially, we show how to get fast algorithms using min-cut and max-flow algorithms. Moreover, we add a regional force to our model which has demonstrated to give superior accuracy for many applications. In the second part, we show that the well-know modularity maximization algorithm is in fact is volume balancing model. Using total variation on graphs, we show that we can turn the modularity maximization into a minimization problem with volume balancing property with a convex energy functional. This is a new observation and also gives some new ways to solve the modularity minimization problems. 
The last part is devoted to study of deep neural networks. We propose some special techniques to add spatial regularization effects to popular deep neural networks. We use numerical experiments to show that the regularized DNN always has smooth boundary when used for image segmentation and similar classification problems. We want to emphasis that our spatial regularization effect is naturally integrated into existing deep neural networks and it only require minimal algorithmic modifications to existing neural networks. It offers very effective stability and smoothing effects into commonly used neural networks. 
转载请注明出处:西安电子科技大学学术信息网
如果您有学术信息或学术动态,欢迎投稿。我们将在第一时间确认并收录,投稿邮箱: meeting@xidian.edu.cn
Copyright © 2011-2019 西安电子科技大学 
开发维护:电子工程学院网络信息中心  管理员:meeting@xidian.edu.cn 站长统计: