Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If you need an accessible version of this item please contact JSTOR User Support

An Entropy Concentration Theorem: Applications in Artificial Intelligence and Descriptive Statistics

Claudine Robert
Journal of Applied Probability
Vol. 27, No. 2 (Jun., 1990), pp. 303-313
DOI: 10.2307/3214649
Stable URL: http://www.jstor.org/stable/3214649
Page Count: 11
  • Read Online (Free)
  • Subscribe ($19.50)
  • Cite this Item
If you need an accessible version of this item please contact JSTOR User Support
An Entropy Concentration Theorem: Applications in Artificial Intelligence and Descriptive Statistics
Preview not available

Abstract

The maximum entropy principle is used to model uncertainty by a maximum entropy distribution, subject to some appropriate linear constraints. We give an entropy concentration theorem (whose demonstration is based on large deviation techniques) which is a mathematical justification of this statistical modelling principle. Then we indicate how it can be used in artificial intelligence, and how relevant prior knowledge is provided by some classical descriptive statistical methods. It appears furthermore that the maximum entropy principle yields to a natural binding between descriptive methods and some statistical structures.

Page Thumbnails

  • Thumbnail: Page 
303
    303
  • Thumbnail: Page 
304
    304
  • Thumbnail: Page 
305
    305
  • Thumbnail: Page 
306
    306
  • Thumbnail: Page 
307
    307
  • Thumbnail: Page 
308
    308
  • Thumbnail: Page 
309
    309
  • Thumbnail: Page 
310
    310
  • Thumbnail: Page 
311
    311
  • Thumbnail: Page 
312
    312
  • Thumbnail: Page 
313
    313