CASIA OpenIR  > 毕业生  > 硕士学位论文
有关分类问题的统计学习理论与算法研究
Alternative TitleStudy of Statistical Learning Theories and Algorithms on Classification Problems
王家琦
Subtype工学硕士
Thesis Advisor王珏
2002-05-01
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
KeywordBayes 统计学习理论 Pac 泛化 经验风险 特征映射 边 缘 间隔 投影 Svm Boosting Bayes Statistical Learning Theory Pac Generalization Empirical Risk Margin Feature Mapping Kernel Svm Boosting
Abstract机器学习一直被认为是经验科学,在泛化性能、计算效率、非线性、模型 简洁程度等几个方面都缺少理论指导。幸运的是,一大批学者一直致力于机器 学习的理论工作。 统计学习理论建立了机器学习泛化性能方面的理论基础,这一理论中的渐 进理论开创性的将概率统计学中"依概率近似"思想引入到机器学习研究当中 并证明了泛函空间的大数定理,从而解决了机器学习当中期望风险与经验风险 之间的关系问题。在此基础上,统计学习理论中的非渐进理论给出了期望风险 依概率成立的界并提出结构风险最小化推理原则,使得有限样本的机器学习具 备了理论基础。PAC学习理论在统计学习理论基础上进一步讨论计算复杂性问 题,使得机器学习计算效率方面的研究也具备了一定的理论基础。核方法为解 决机器学习的非线性问题提供了一个崭新的思路。有关某个具体算法下的模型 简洁性的结论也已经被证明。这些都说明机器学习正逐渐成为一门真正的科 学。 从上述几个机器学习的评价标准出发,本文共分成两部分: 1、第一部分“机器学习的统计基础”是本文作者对相关理论和方法的评 述; 2、第二部分“机器学习的几何基础”是本文作者的工作重点,包括核方法 的几何解释、通用核的理论依据、SVM的几何算法,此外,在这一部分当中, 还对Boosting方法进行了评述。
Other AbstractMachine Learning has been regarded as the empirical science for a long time. There is no the theoretical foundation for the following problems concerned by machine learning: generalization error, computational cost, nonlinear, description length of learning model and so on. Fortunately, many researchers have been devoted to establishing the theory on machine learning. Generalization of machine learning is based on statistical learning theory. Based on this theory, PAC theory is established to guide the research on computational complexity of machine learning. Kernel method is a new way to solve nonlinear problems in machine learning. The above facts show that machine learning is becoming a really science step by step. This thesis includes two parts. Statistical properties of machine learning are introduced in the first part. My research is focused on the second part "Geometry foundation of machine learning" including theoretical analysis of universal kernel functions, geometrical algorithm for SVM. Insides, boosting will be introduced in this part.
shelfnumXWLW632
Other Identifier632
Language中文
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/6834
Collection毕业生_硕士学位论文
Recommended Citation
GB/T 7714
王家琦. 有关分类问题的统计学习理论与算法研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2002.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王家琦]'s Articles
Baidu academic
Similar articles in Baidu academic
[王家琦]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王家琦]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.