JAIST Repository >
School of Knowledge Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/10930

Title: 統計的モデルの考え方 : 確率分布から多変量解析まで
Authors: 日高, 昇平
西田, 豊
Keywords: 認知モデル
統計的モデル
多変量解析
Issue Date: 2012-03-22
Publisher: 日本認知科学会
Magazine name: 日本認知科学会・学習と対話研究分科会・第46回研究会
Volume: 2012
Number: 1
Start page: 21
End page: 26
Abstract: In the present manuscript, we introduce a basic idea underlying statistical modeling as application for research in cognitive science. In order to introduce the minimum prerequisites, a hypothetical case was studied using binomial distribution as a binary decision making model. Walking through this case study, the idea of probability distribution, model selection, statistical test, and parameter estimation were briefly outlined. In the latter half of the paper, we studied a multivariate clustering model, structure discovery process from unlabeled data, as similarity judgment on conceptual space. The underlying assumption, parameter estimation, and interpretation of parameters in terms of cognitive process were discussed.
Rights: 日高 昇平, 西田 豊, 日本認知科学会・学習と対話研究分科会・第46回研究会, 2012(1), 2012, 21-26.
URI: http://hdl.handle.net/10119/10930
Material Type: publisher
Appears in Collections:a11-1. 会議発表論文 (Conference Papers)

Files in This Item:

File Description SizeFormat
18012.pdf523KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology