Advances in Minimum Description Length: Theory and Applications (Hardcover)
暫譯: 最小描述長度的進展:理論與應用(精裝版)
Peter D. Grunwald, In Jae Myung, Mark A. Pitt
- 出版商: MIT
- 出版日期: 2005-02-25
- 售價: $1,550
- 語言: 英文
- 頁數: 372
- 裝訂: Hardcover
- ISBN: 0262072629
- ISBN-13: 9780262072625
-
相關分類:
Machine Learning、機率統計學 Probability-and-statistics、Data Science
立即出貨(限量) (庫存=5)
買這商品的人也買了...
-
$700$630 -
$590$466 -
$720$569 -
$980$774 -
$850$723 -
$750$593 -
$490$382 -
$620$490 -
$680$578 -
$650$507 -
$650$514 -
$1,900$1,805 -
$590$460 -
$620$490 -
$580$452 -
$590$460 -
$580$452 -
$680$537 -
$680$537 -
$650$507 -
$599$473 -
$980$774 -
$720$569 -
$850$765 -
$600$480
商品描述
Description:
The process of inductive inference -- to infer general laws and principles from particular instances -- is the basis of statistical modeling, pattern recognition, and machine learning. The Minimum Descriptive Length (MDL) principle, a powerful method of inductive inference, holds that the best explanation, given a limited set of observed data, is the one that permits the greatest compression of the data -- that the more we are able to compress the data, the more we learn about the regularities underlying the data. Advances in Minimum Description Length is a sourcebook that will introduce the scientific community to the foundations of MDL, recent theoretical advances, and practical applications.
The book begins with an extensive tutorial on MDL, covering its theoretical underpinnings, practical implications as well as its various interpretations, and its underlying philosophy. The tutorial includes a brief history of MDL -- from its roots in the notion of Kolmogorov complexity to the beginning of MDL proper. The book then presents recent theoretical advances, introducing modern MDL methods in a way that is accessible to readers from many different scientific fields. The book concludes with examples of how to apply MDL in research settings that range from bioinformatics and machine learning to psychology.
Peter D. Grünwald is a researcher at CWI, the National Research Institute for Mathematics and Computer Science, Amsterdam, the Netherlands. He is also affiliated with EURANDOM, the European Research Institute for the Study of Stochastic Phenomena, Eindhoven, the Netherlands.
In Jae Myung is Professor in the Department of Psychology and a member of the Center for Cognitive Science at Ohio State University.
Mark A. Pitt is Professor in the Department of Psychology and a member of the Center for Cognitive Science at Ohio State University.
Table of Contents:
Series Foreword vii Preface ix I Introductory Chapters 1 1 Introducing the Minimum Description Length Principle
Peter D. Grünwald3 2 Minimum Description Length Tutorial
Peter D. Grünwald23 3 MDL, Bayesian Inference, and the Geometry of the Space of Probability Distributions
Vijay Balasubramanian81 4 Hypothesis Testing for Poisson vs. Geometric Distributions Using Stochastic Complexity
Aaron D. Lanterman99 5 Applications of MDL to Selected Families of Models
Andrew J. Hanson and Philip Chi-Wing Fu125 6 Algorithmic Statistics and Kolmogorov's Structure Functions
Paul Vitányi151 II Theoretical Advances 175 7 Exact Minimax Predictive Density Estimation and MDL
Feng Liang and Andrew Barron177 8 The Contribution of Parameters to Stochastic Complexity
Dean P. Foster and Robert A. Stine195 9 Extended Stochastic Complexity and Its Applications to Learning
Kenji Yamanishi215 10 Kolmogorov's Structure Function in MDL Theory and Lossy Data Compression
Jorma Rissanen and Ioan Tabus245 III Practical Applications 263 11 Minimum Message Length and Generalized Bayesian Nets with Asymmetric Languages
Joshua W. Comley and David L. Dowe265 12 Simultaneous Clustering and Subset Selection via MDL
Rebecka Jörnsten and Bin Yu295 13 An MDL Framework for Data Clustering
Petri Kontkanen, Petri Myllymäki, Wray Buntine, Jorma Rissanen and Henry Tirri323 14 Minimum Description Length and Psychological Clustering Models
Michael D. Lee and Daniel J. Navarro355 15 A Minimum Description Length Principle for Perception
Nick Chater385 16 Minimum Description Length and Cognitive Modeling
Yong Su, In Jae Myung and Mark A. Pitt411 Index 435
商品描述(中文翻譯)
描述:
歸納推理的過程——從特定實例推斷一般法則和原則——是統計建模、模式識別和機器學習的基礎。最小描述長度(Minimum Descriptive Length, MDL)原則是一種強大的歸納推理方法,認為在給定有限觀察數據的情況下,最佳解釋是能夠最大程度壓縮數據的解釋——我們能夠壓縮數據的越多,就越能了解數據背後的規律。《最小描述長度的進展》是一本將向科學界介紹MDL基礎、最近的理論進展和實際應用的資料來源書籍。
本書以MDL的廣泛教程開始,涵蓋其理論基礎、實際意涵及其各種解釋,以及其背後的哲學。教程包括MDL的簡史——從其根源於Kolmogorov複雜度的概念到MDL的正式開始。接著,本書介紹了最近的理論進展,以易於不同科學領域讀者理解的方式介紹現代MDL方法。本書最後提供了如何在從生物資訊學和機器學習到心理學等研究環境中應用MDL的範例。
彼得·D·格倫瓦爾德(Peter D. Grünwald)是荷蘭阿姆斯特丹數學與計算機科學國家研究所(CWI)的研究員。他同時也與荷蘭埃因霍溫的歐洲隨機現象研究所(EURANDOM)有關聯。
閔在(In Jae Myung)是俄亥俄州立大學心理學系的教授,也是認知科學中心的成員。
馬克·A·皮特(Mark A. Pitt)是俄亥俄州立大學心理學系的教授,也是認知科學中心的成員。
目錄:
系列前言
前言
引言章節
1. 介紹最小描述長度原則
彼得·D·格倫瓦爾德
2. 最小描述長度教程
彼得·D·格倫瓦爾德
3. MDL、貝葉斯推理與概率分佈空間的幾何
維賈伊·巴拉蘇布拉馬尼安
4. 使用隨機複雜度進行泊松與幾何分佈的假設檢驗
亞倫·D·蘭特曼
5. MDL在選定模型家族中的應用
安德魯·J·漢森與傅志榮
6. 算法統計與Kolmogorov的結構函數
保羅·維塔伊尼
II. 理論進展
7. 精確的最小最大預測密度估計與MDL
馮·梁與安德魯·巴倫
8. 參數對隨機複雜度的貢獻
迪恩·P·福斯特與羅伯特·A·斯坦
9. 擴展隨機複雜度及其在學習中的應用
山西健二
10. MDL理論中的Kolmogorov結構函數與有損數據壓縮
約爾馬·里薩嫩與伊奧安·塔布斯
III. 實際應用
11. 最小消息長度與不對稱語言的廣義貝葉斯網絡
約書亞·W·科姆利與大衛·L·道威
12. 通過MDL進行同時聚類與子集選擇
瑞貝卡·約恩斯滕與余彬
13. 一個用於數據聚類的MDL框架
佩特里·孔特卡寧、佩特里·米利馬基、維瑞·班廷、約爾馬·里薩嫩與亨利·提里
14. 最小描述長度與心理聚類模型
邁克·D·李與丹尼爾·J·納瓦羅
15. 感知的最小描述長度原則
尼克·查特