CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
统计机器学习中参数可辨识性研究及其关键问题
冉志勇1; 胡包钢2
Source Publication自动化学报
2017
Volume43Issue:10Pages:1677-1686
Other AbstractThe study of parameter identifiability has important theoretical meaning and practical value in statistical machine learning. Parameter identifiability is a property that concerns whether the model parameters can be uniquely determined. In learning models containing physical parameters, identifiability is a prerequisite for estimating those parameters; more  importantly, it reflects the physical characteristic determined by those parameters. In order to extend our perspective to future human-like intelligent machines, we put the learning models into the framework of "knowledge-and data-driven models". Within this framework, we propose two key issues. The first is about identifiability criteria which aim to study various criteria closely related to identifiability; the coupling manner between knowledge-driven submodel and data-driven submodel provides novel topics for identifiability study. The second focuses on identifiability relevant to theory and application in machine learning; this involves the deep influence of identifiability on parameter estimation, model selection, learning algorithms, learning dynamics, Bayesian inference.
Keyword可辨识性 统计机器学习 参数估计 奇异学习理论 贝叶斯推断
DOI10.16383/j.aas.2017.c160720
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19990
Collection模式识别国家重点实验室_多媒体计算与图形学
Corresponding Author冉志勇
Affiliation1.重庆邮电大学计算机科学与技术学院计算智能重庆市重点实验室
2.中国科学院自动化研究所模式识别国家重点实验室
Recommended Citation
GB/T 7714
冉志勇,胡包钢. 统计机器学习中参数可辨识性研究及其关键问题[J]. 自动化学报,2017,43(10):1677-1686.
APA 冉志勇,&胡包钢.(2017).统计机器学习中参数可辨识性研究及其关键问题.自动化学报,43(10),1677-1686.
MLA 冉志勇,et al."统计机器学习中参数可辨识性研究及其关键问题".自动化学报 43.10(2017):1677-1686.
Files in This Item: Download All
File Name/Size DocType Version Access License
统计机器学习中参数可辨识性研究及其关键问(1371KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[冉志勇]'s Articles
[胡包钢]'s Articles
Baidu academic
Similar articles in Baidu academic
[冉志勇]'s Articles
[胡包钢]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[冉志勇]'s Articles
[胡包钢]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 统计机器学习中参数可辨识性研究及其关键问题.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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