Advertisement

From Statistical Physics to Statistical Inference and Back

  • Peter Grassberger
  • Jean-Pierre Nadal

Part of the NATO ASI Series book series (ASIC, volume 428)

Table of contents

  1. Front Matter
    Pages i-viii
  2. In place of an Introduction

    1. Gérard Toulouse
      Pages 1-9
  3. Principles for Inference

  4. Coding and Statistical Physics of Disordered Systems

    1. Sergio Verdu
      Pages 155-167
    2. Marc Mézard
      Pages 183-193
    3. Nicolas Sourlas
      Pages 195-204
  5. Learning

    1. Ralph Linsker
      Pages 237-247
    2. H.-U. Bauer, T. Geisel, K. Pawelzik, F. Wolf
      Pages 249-261
  6. Dynamical Systems

  7. Quantum Mechanics

  8. Back Matter
    Pages 351-355

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 long-standing 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.

Keywords

Bayesian inference Chaos Minimum Description Length SPIN Statistical Physics Symbol complexity error-correcting code information information theory learning uncertainty

Editors and affiliations

  • Peter Grassberger
    • 1
  • Jean-Pierre Nadal
    • 2
  1. 1.Department of Theoretical PhysicsUniversity of WuppertalWuppertalGermany
  2. 2.Laboratory of Statistical PhysicsÉcole Normale SupérieureParisFrance

Bibliographic information

  • DOI https://doi.org/10.1007/978-94-011-1068-6
  • Copyright Information Kluwer Academic Publishers 1994
  • Publisher Name Springer, Dordrecht
  • eBook Packages Springer Book Archive
  • Print ISBN 978-94-010-4465-3
  • Online ISBN 978-94-011-1068-6
  • Series Print ISSN 1389-2185
  • Buy this book on publisher's site
Industry Sectors
Materials & Steel
Chemical Manufacturing
Biotechnology
Energy, Utilities & Environment