[Adapt] [Seminar] Prototype-based Learning on Concept-drifting Data Streams

[LiuYi]

Hi Adapters,

Our seminar will take place tomorrow at 5pm in room SEIEE 3-528. This time, I will introduce a prototype-based classification model for evolving data streams, called SyncStream.

Data stream classification is a challenging data mining task because of two important properties: potentially infinite length and evolving nature. Currently, there are two main strategies to mine evolving data streams: single model learning and ensemble learning.

I will discuss the drawbacks of these two traditional learning strategies and show you the basic idea and the advantages of the new prototype-based learning method.

Hope you can enjoy the talk.

Best,
Yi


-------------------------
Department of Computer Science and Engineering 
Shanghai Jiao Tong University
800 Dongchuan Road, Shanghai, China
Email：liuyi61ly at hotmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20151110/ae4151ad/attachment-0001.html>