报告嘉宾:彭冲(青岛大学)
报告时间:2018年05月16日(星期三)晚上20:00(北京时间)
报告题目:Learning 2D features of 2D data for clustering
主持人:张健(King Abdullah University of Science and Technology)
报告人简介:
彭冲毕业于南伊利诺伊大学,2017年获计算机科学博士学位,现为青岛大学计算机科学技术学院讲师,青岛大学青年卓越人才。他在AAAI,KDD,CVPR,ICDM,CIKM,ICDE等会议和IEEE TGRS,SPL,ACM TKDD,TIST等期刊发表论文20余篇。
个人主页:
http://cst.qdu.edu.cn/info/1021/2569.htm
相关文献:
1. Subspace clustering using log-determinant rank approximation, Chong Peng, Zhao Kang, Huiqing Li, Qiang Cheng, KDD 2015.
2. Subspace clustering via variance regularized ridge regression, Chong Peng, Zhao Kang, Qiang Cheng, CVPR 2017.
3. Integrate and conquer: double-sided two-dimensional k-means via integrating of projection and manifold construction, ACM TIST, to appear.
报告摘要:
As fundamental task in unsupervised learning, clustering has been widely studied in data mining and machine learning community. When the inputs are 2-dimensional (2D) data, most existing clustering methods convert such data to vectors as preprocessing, which severely damages spatial information of the data. How to preserve 2D features of the data in the learning process is a key problem. In this talk, I will introduce a novel method for clustering 2D data. First, I will introduce the subspace clustering theory. Based on this, I will then present subspace clustering via variance regularized ridge regression. In addition, I will present a generalized way for clustering 2D data by extending K-means to 2D scenario.
参与方式:
长按或扫描下方二维码,关注”VALSE“微信公众号(valse_wechat),后台回复”13期“,获取直播地址。
特别鸣谢本次Webinar主要组织者:
VOOC责任委员:张健(King Abdullah University of Science and Technology)
VODB协调理事:郑海永(中国海洋大学)
活动参与方式:
1、VALSE Webinar活动依托在线直播平台进行,活动时讲者会上传PPT或共享屏幕,听众可以看到Slides,听到讲者的语音,并通过聊天功能与讲者交互;
2、为参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ群(目前A、B、C、D、E、F、G群已满,除讲者等嘉宾外,只能申请加入VALSE H群,群号:701662399);
*注:申请加入VALSE QQ群时需验证姓名、单位和身份,缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。
3、在活动开始前5分钟左右,讲者会开启直播,听众点击直播链接即可参加活动,支持安装Windows系统的电脑、MAC电脑、手机等设备;
4、活动过程中,请不要说无关话语,以免影响活动正常进行;
5、活动过程中,如出现听不到或看不到视频等问题,建议退出再重新进入,一般都能解决问题;
6、建议务必在速度较快的网络上参加活动,优先采用有线网络连接;
7、VALSE微信公众号会在每周一推送上一周Webinar报告的总结及视频(经讲者允许后),每周四发布下一周Webinar报告的通知及直播链接。