传统机器学习算法需要利用大量有标记的（labeled）样本进行学习。随着信息技术的飞速发展，收集大量未标记的（unlabeled）样本已相当容易，如何利用大量的未标记样本来改善学习性能成为当前机器学习研究中备受关注的问题。半监督学习（semi-supervisedlearning）是利用

标题:[zz]IanHorrocks:大器中成 发信站:瀚海星云(2007年09月13日01:26:00星期四),站内信件 这篇文章是我师兄写的，做过SemanticWeb的人肯定都知道IanHorrocks，看了他的成 才历程，真不容易，而且文中很多做科研的想法，也很有启发。和各位共勉～ [zz] http://boole.cs.

⒈ 如果一块黑板就是一片浩淼的大海,那么,老师便是海上一名优秀的水手。铃声响起那刻，你用教鞭作桨，划动那船只般泊在港口的课本。课桌上，那难题堆放，犹如暗礁一样布列。你手势生动如一只飞翔的鸟，在讲台上挥一条优美弧线船只穿过天空飘不来一片云，犹如你亮堂堂的

WASHINGTON Some lending companies with access to a national database that contains confidential information on 60 million student borrowers have repeatedly searched it in ways that violate federal rules, raising alarms about data mining and abuse of

Recently, I have had several projects that required me to identify experts in a subject area. When the field of expertise is scientific or medical, often the best way to identify experts is see who has published papers on a topic and who is frequent

Geoffrey Bilder contends that, when asked to deliver this session for UKSG, I knew nothing about text mining. By the end of today's session, I suspected this was purely a comedy opener - either that, or he's really done his homework in the meantime.

Qiang Yang qyang (at) cs (dot) ust (dot) hk Phone : (00852) 2358-8768 Fax: (00852) 2358-1477 Address : Department of Computer Science, Hong Kong University of Science and Technology, Clearwater Bay, Kowloon, Hong Kong Room 3563 (Lift 27/28) Research

Something about me I graduated at the Computer Science Department ( DSI ) of the University of Milano ; my graduation thesis was about concurrency and domain theory, and it was titled Automi concorrenti e teoria dei domini (Concurrent Automata and D