Evolution programs for Bayesian training of neural networks

Lemuel R. Myers Jr.; John G. Keller; Steven K. Rogers; Matthew Kabrisky

doi:10.1117/12.304793

25 March 1998 Evolution programs for Bayesian training of neural networks

Lemuel R. Myers Jr., John G. Keller, Steven K. Rogers, Matthew Kabrisky

Proceedings Volume 3390, Applications and Science of Computational Intelligence; (1998) https://doi.org/10.1117/12.304793
Event: Aerospace/Defense Sensing and Controls, 1998, Orlando, FL, United States

Abstract

In this paper, it is shown that Evolution Programs can be used to search the weight space for Bayesian training of a Neural Network. Bayesian Analysis is an integration problem (as opposed to an optimization problem) over weight space. The first application of the Bayesian method primarily focused on using a Gaussian approximation of the posterior distribution in an area of high probability in the weight space instead of using formal integration. More recently, training a neural network in a Bayesian fashion has been accomplished by searching weight space for areas of high probability density which obviates the need for the Gaussian assumption. In particular, a hybrid Monte-Carlo method was used to search weight space in a logical manner to obtain an arbitrarily close approximation of the integration involved in a Bayesian analysis. Genetic Algorithms have been used in the past to determine the weights in an ANN, and (with some slight modifications) are ideally suited for searching the weight space to approximate the Bayesian integration. In this respect, the Bayesian framework provides a simple and elegant way to apply Evolution Programs to the ANN training problem. While this paper concentrates on using ANNs as classifiers, the generalization to regression problems is straightforward.

Citation Download Citation

Lemuel R. Myers Jr., John G. Keller, Steven K. Rogers, and Matthew Kabrisky "Evolution programs for Bayesian training of neural networks", Proc. SPIE 3390, Applications and Science of Computational Intelligence, (25 March 1998); https://doi.org/10.1117/12.304793

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available