Table of contents

In place of an Introduction

Principles for Inference

Coding and Statistical Physics of Disordered Systems

Learning

Dynamical Systems
About this book
Introduction
Physicists, when modelling physical systems with a large number of degrees of freedom, and statisticians, when performing data analysis, have developed their own concepts and methods for making the `best' inference. But are these methods equivalent, or not? What is the state of the art in making inferences? The physicists want answers. More: neural computation demands a clearer understanding of how neural systems make inferences; the theory of chaotic nonlinear systems as applied to time series analysis could profit from the experience already booked by the statisticians; and finally, there is a longstanding conjecture that some of the puzzles of quantum mechanics are due to our incomplete understanding of how we make inferences. Matter enough to stimulate the writing of such a book as the present one.
But other considerations also arise, such as the maximum entropy method and Bayesian inference, information theory and the minimum description length. Finally, it is pointed out that an understanding of human inference may require input from psychologists. This lively debate, which is of acute current interest, is well summarized in the present work.
But other considerations also arise, such as the maximum entropy method and Bayesian inference, information theory and the minimum description length. Finally, it is pointed out that an understanding of human inference may require input from psychologists. This lively debate, which is of acute current interest, is well summarized in the present work.
Keywords
Bayesian inference Chaos Minimum Description Length SPIN Statistical Physics Symbol complexity errorcorrecting code information information theory learning uncertainty
Editors and affiliations
Bibliographic information
 Book Title From Statistical Physics to Statistical Inference and Back

Editors
P. Grassberger
J.P. Nadal
 Series Title NATO ASI Series
 DOI https://doi.org/10.1007/9789401110686
 Copyright Information Kluwer Academic Publishers 1994
 Publisher Name Springer, Dordrecht
 eBook Packages Springer Book Archive
 Hardcover ISBN 9780792327752
 Softcover ISBN 9789401044653
 eBook ISBN 9789401110686
 Series ISSN 13892185
 Edition Number 1
 Number of Pages VIII, 355
 Number of Illustrations 0 b/w illustrations, 0 illustrations in colour

Topics
Thermodynamics
Complex Systems
Coding and Information Theory
Artificial Intelligence
Statistical Physics and Dynamical Systems
 Buy this book on publisher's site