Home | Contact | Sitemap | 中文 | CAS
Search: 
Home │  About Us │  Research │  People │  International Cooperation │  Education & Training │  Papers
  Seminar
Conference
Forum on FS
Colloquium
Seminar
Lunch Seminar
Coffee Time
Advanced Course
KITPC Activities
Other activities
  Location: Home >  Research Activities >  Seminar
Tree models and its application in search engine
2013-04-15     Text Size:  A
Institute of Theoretical Physics
Chinese Academy of Sciences
学术报告
Title
题目
Tree models and its application in search engine
Speaker
报告人
Dr. Jie Zhou (周杰 博士)
Baidu (百度公司)
Date
日期
2013-04-15 PM 16:00 Monday
Venue
地点
Conference Hall 322, ITP/理论物理所322报告厅
Abstract
摘要

近些年来,以Decision Tree为基础的树类模型(Gradient Boosting Decision Tree, Gradient Boosting Ranking Model, Random Forest),在回归和排序问题上得到了广泛的应用,而这正是主流搜索引擎各个子模块的基础。主体部分我们将从两条线来进行介绍。首先,我们将介绍当前搜索引擎的主流架构模式以及在不同层面所面对的问题。另外,我们将对比树模型和传统方法在解决该问题时效果上的差异。在主体之外,我们还将简单概括最近5年刚刚兴起的Deep Neural Network对机器学习领域的影响。

  Appendix:
       Address: No. 55 Zhong Guan Cun East Road, Haidian District, Beijing 100190, P. R. China
Copyright ? Institute of Theoretical Physics, Chinese Academy of Sciences, All Rights Reserved