CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
冉志勇1; 胡包钢2
Source Publication自动化学报
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
Citation statistics
Document Type期刊论文
Corresponding Author冉志勇
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
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.