A Caltech Library Service

Probability Estimation from a Database Using a Gibbs Energy Model

Miller, John W. and Goodman, Rodney M. (1993) Probability Estimation from a Database Using a Gibbs Energy Model. In: Advances in Neural Information Processing Systems 5 (NIPS 1992). Advances in Neural Information Processing Systems. No.5. Morgan Kaufmann , San Mateo, CA, pp. 531-538. ISBN 1-55860-274-7.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present an algorithm for creating a neural network which produces accurate probability estimates as outputs. The network implements a Gibbs probability distribution model of the training database. This model is created by a new transformation relating the joint probabilities of attributes in the database to the weights (Gibbs potentials) of the distributed network model. The theory of this transformation is presented together with experimental results. One advantage of this approach is the network weights are prescribed without iterative gradient descent. Used as a classifier the network tied or outperformed published results on a variety of databases.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1993 Morgan Kaufmann. This work is funded in part by DARPA and ONR under grant N00014-92-J-1860.
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Office of Naval Research (ONR)N00014-92-J-1860
Series Name:Advances in Neural Information Processing Systems
Issue or Number:5
Record Number:CaltechAUTHORS:20160127-132508165
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:64019
Deposited By: Kristin Buxton
Deposited On:27 Jan 2016 22:23
Last Modified:03 Oct 2019 09:33

Repository Staff Only: item control page