报告题目：Monitoring of BD3 -- Big, Dynamic, Distributed Data（可信计算论坛）
报告人：Daniel Keren 教授
报告时间：2015年4月29 日 14:00——15:30
主办单位：软件学院 科技处 国际交流处
Phd at Hebrew University, computer science, 1991.Post-doctoral work at Brown University, 1991-1994.Since 1994, with the Department of Computer Science, University of Haifa.Main research areas: machine learning and classification over large data; monitoring large, dynamic, distributed data.Currently participating in two EU research projects.
1) Title: Monitoring of BD3 -- Big, Dynamic, Distributed Data
In this talk, I will survey algorithms to monitor BD3, which attempt to reduce communication and computational complexity. The proposed approach relies on geometric considerations which are quite intuitive to grasp.
2) Title: Big Data Classification Using a Background Prior
A canonical problem in machine learning is category classification (e.g. find all instances of human faces, cars etc., in an image). In this talk I will describe an efficient and easy to apply classification algorithm, which replaces the negative samples by a prior and then constructs a "hybrid" classifier that separates the positive samples from this prior. The resulting classifier achieves an identical or better classification rate than SVM, while requiring far smaller memory and lower computational complexity to train and apply.