A Caltech Library Service

Objective Functions For Neural Network Classifier Design

Goodman, Rod and Miller, John W. and Smyth, Padhraic (1991) Objective Functions For Neural Network Classifier Design. In: Proceedings. 1991 IEEE International Symposium on Information Theory. IEEE , Piscataway, NJ, p. 87. ISBN 0-7803-0056-4.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Backpropagation was originally derived in the context of minimizing a mean-squared error (MSE) objective function. More recently there has been interest in objective functions that provide accurate class probability estimates. In this talk we derive necessary and sufficient conditions on the required form of an objective function to provide probability estimates. This leads to the definition of a general class of functions which includes MSE and cross entropy (CE) as two of the simplest cases. We establish the equivalence of these functions to Maximum Likelihood estimation and the more general principle of Minimum Description Length models. Empirical results are used to demonstrate the tradeoffs associated with the choice of objective functions which minimize to a probability.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1991 IEEE. The research described in this talk was carried out in part by the Jet Propulsion Laboratories, California Institute of Technology, under a contract with the National Aeronautics and Space Administration. In addition this work was supported in part by the Air Force Office of Scientific Research under grant number AFOSR-90-0199.
Funding AgencyGrant Number
Air Force Office of Scientific Research (AFOSR)90-0199
Record Number:CaltechAUTHORS:20170620-163501947
Persistent URL:
Official Citation:R. Goodman, J. W. Miller and P. Smyth, "Objective Functions For Neural Network Classifier Design," Proceedings. 1991 IEEE International Symposium on Information Theory, 1991, pp. 87-87. doi: 10.1109/ISIT.1991.695143
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:78392
Deposited On:21 Jun 2017 18:12
Last Modified:15 Nov 2021 17:39

Repository Staff Only: item control page