このエントリーをはてなブックマークに追加
ID 30056
FullText URL
Author
Tanaka, Masahiro
Kotokawa, Yasuaki
Tanino, Tetsuzo
Abstract

In this paper, pattern classification by stochastic neural networks is considered. This model is also called a Gaussian mixture model. When missing data exist in the training data, it is usual to remove incomplete instants. Here we take another approach, where the missing elements are estimated by using the conditional expectation based on the estimated model by using the EM algorithm. It is shown by using Fisher's Iris data that this approach is superior to removing incomplete data

Keywords
learning (artificial intelligence)
neural nets
parameter estimation
pattern classification
probability
Note
Digital Object Identifier: 10.1109/ICSMC.1996.569878
Published with permission from the copyright holder. This is the institute's copy, as published in Systems, Man, and Cybernetics, 1996., IEEE International Conference on, 14-17 Oct. 1996, Vol. 1, Pages 690-695.
Publisher URL:http://dx.doi.org/10.1109/ICSMC.1996.569878
Copyright © 1996 IEEE. All rights reserved.
Published Date
1996-10
Publication Title
Systems
Volume
volume1
Start Page
690
End Page
695
Content Type
Journal Article
language
英語
Refereed
True
DOI
Submission Path
industrial_engineering/54