Paul B. Kantor
ABSTRACT
Applications, assumptions and properties of the maximum entropy principle are discussed. The maximum entropy principle integrates prior estimates of relevance with the observed distribution of term combinations. The result may be a reordering of the segments of a database, compared to a naive estimate. Numerical examples obtained by solution of the non-linear equations for the dual variables are presented and discussed.
* Supported in part by the National Science Foundation under grant IST-8318630.
- CALV81.CALVINO, ltalo "Se una notre d'inverno un viasgiacore (Zf on a winter's night a traveler), Harcourt Brace Jovanovich, p260, c1981.Google Scholar
- CHEE83.CI#gSSEHAN, Peter "A method of computing maximum-entropy probability values for expert system"p Proceedlnss of the 3rd Annual Workshop on Bayesian liethods in Applied Statistics; C. Ray Smith (ed). Laramie, WY: University of WyominS; (1983)Google Scholar
- COOP83.COOPER, 9. S. "Exploiting the maximum entropy principle to increase retrieval effectiveness", J. Am. Soc. Inf. Sci., v34nl pp31-39 (1983 ). .Google ScholarCross Ref
- COOP82.COOPER, W. S. and HUIZINGA, P. "The maximum entropy principle and its application to the desiKn of prnbabillstic retrieval system", Inf. Technol: Res. &Dev,, vln2pp99-112 (1982).Google Scholar
- GOOD63.GOOD, I. J. "Maximum entropy for hypothesis #ormulation, especially for mu ttidimens~onal contingency tables" Ann Hath. Star. v34ppgll-932 (1963).Google Scholar
- GUID83.GUIDA, Giovanni and TASSO, C. "An Expert Intermediary System for Interactive Document Retrieval, &utomatica, vlgn6p759-766, November 1983. IR-NLZ.Google Scholar
- JAYN82.JAYNES, Edwin T. 'son the rational of maximum entropy methods"p Proceedings of the IEES, v70ng, September, 1982.Google Scholar
- KANT84.KANTOR, Paul B. "Maximum Entropy and the Optimal Des;sn o~ Automated Information Retrieval Systems." Information Technolosy ; v3n2pp88-g& (1984).Google Scholar
- KHIN67.#INCHIN, A. I. "Foundations of statistical mechanics", Dover, USA (1967)Google Scholar
- SALT83.SALTON, Gerard "Introduction to modern information retrleval", HcGraw-Ri11, #8p, c(1983). Google ScholarDigital Library
- YU83.YU, C. T., BUCKLE~, C., LAN, K., SALTON, O., "A generalized term dependence model in information retrieval", Technical report TR 83-543, Department of Computer Science, Cornel1 University (1983). Google ScholarDigital Library
Recommendations
The Latent Maximum Entropy Principle
We present an extension to Jaynes’ maximum entropy principle that incorporates latent variables. The principle of latent maximum entropy we propose is different from both Jaynes’ maximum entropy principle and maximum likelihood estimation, but can yield ...
Boltzmann machine learning with the latent maximum entropy principle
UAI'03: Proceedings of the Nineteenth conference on Uncertainty in Artificial IntelligenceWe present a new statistical learning paradigm for Boltzmann machines based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes' maximum entropy principle and from standard maximum ...
Learning mixture models with the latent maximum entropy principle
ICML'03: Proceedings of the Twentieth International Conference on International Conference on Machine LearningWe present a new approach to estimating mixture models based on a new inference principle we have proposed: the latent maximum entropy principle (LME). LME is different both from Jaynes' maximum entropy principle and from standard maximum likelihood ...
Comments