BOLTZMANN MACHINE AS A STATISTICAL MODEL

• Nagaoka Hiroshi

  Graduate School of Information Systems, The University of Electro-Communicatons

• Kojima Tetsuya

  Graduate School of Engineering, Hokkaido University

Bibliographic Information

Other Title

• 統計的モデルとしてのボルツマンマシン

Abstract

A Boltzmann machine is known as a stochastically exteded model of the Hopfield neural network. It is not only a neural network model but related to various fields, such as statistics, statistical mechanics, information geometry, and so on. We review various aspects of a Boltzmann machine such as dynamics, learning rule, maximum entropy property, spatial Markovian property, and so on, in view of the general theories of Gibbs sampler, expontial family and Markov random field. Some recent studies on the application of Boltzmann machines are also reviewed.

Journal

• Bulletin of the Computational Statistics of Japan

  Bulletin of the Computational Statistics of Japan 8 (1), 61-81, 1995

  Japanese Society of Computational Statistics

Keywords

• Gibbs smplar
• Exponential family
• Markov random field

Details

• CRID: 1390282679360269056
• NII Article ID: 110001236362
• NII Book ID: AN10195854
• DOI: 10.20551/jscswabun.8.1_61
• ISSN: 21899789
• ISSN: 09148930
• Text Lang: ja
• Data Source:
  • JaLC
  • CiNii Articles
• Abstract License Flag: Disallowed