Neurodynamics of learning and network performance

Charles L. Wilson; James L. Blue; Omid M. Omidvar

doi:10.1117/12.272656

1 July 1997 Neurodynamics of learning and network performance

Charles L. Wilson, James L. Blue, Omid M. Omidvar

Author Affiliations +

Journal of Electronic Imaging, Vol. 6, Issue 3, (July 1997). https://doi.org/10.1117/12.272656

Abstract

A simple dynamic model of a neural network is presented. Using the dynamic model of a neural network, we improve the performance of a three-layer multilayer perceptron (MLP). The dynamic model of a MLP is used to make fundamental changes in the network optimization strategy. These changes are: Neuron activation functions are used, which reduce the probability of singular Jacobians; Successive regularization is used to constrain the volume of the weight space being minimized; Boltzmann pruning is used to constrain the dimension of the weight space; and prior class probabilities are used to normalize all error calculations, so that statistically significant samples of rare but important classes can be included without distortion of the error surface. All four of these changes are made in the inner loop of a conjugate gradient optimization iteration and are intended to simplify the training dynamics ofthe optimization. On handprinted digits and fingerprint classification problems, these modifications improve error-reject performance by factors between 2 and 4 and reduce network size by 40 to 60%.

Citation Download Citation

Charles L. Wilson, James L. Blue, and Omid M. Omidvar "Neurodynamics of learning and network performance," Journal of Electronic Imaging 6(3), (1 July 1997). https://doi.org/10.1117/12.272656

Published: 1 July 1997

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