Statistical learning from nonrecurrent experience with discrete input variables and recursive-error-minimization equations

Jeffrey R. Carter; Wayne E. Simon

doi:10.1117/12.21211

1 August 1990 Statistical learning from nonrecurrent experience with discrete input variables and recursive-error-minimization equations

Jeffrey R. Carter, Wayne E. Simon

Author Affiliations +

Proceedings Volume 1294, Applications of Artificial Neural Networks; (1990) https://doi.org/10.1117/12.21211
Event: 1990 Technical Symposium on Optics, Electro-Optics, and Sensors, 1990, Orlando, FL, United States

Abstract

Neural networks are trained using Recursive Error Minimization (REM) equations to perform statistical classification. Using REM equations with continuous input variables reduces the required number of training experiences by factors of one to two orders of magnitude over standard back propagation. Replacing the continuous input variables with discrete binary representations reduces the number of connections by a factor proportional to the number of variables reducing the required number of experiences by another order of magnitude. Undesirable effects of using recurrent experience to train neural networks for statistical classification problems are demonstrated and nonrecurrent experience used to avoid these undesirable effects. 1. THE 1-41 PROBLEM The statistical classification problem which we address is is that of assigning points in ddimensional space to one of two classes. The first class has a covariance matrix of I (the identity matrix) the covariance matrix of the second class is 41. For this reason the problem is known as the 1-41 problem. Both classes have equal probability of occurrence and samples from both classes may appear anywhere throughout the ddimensional space. Most samples near the origin of the coordinate system will be from the first class while most samples away from the origin will be from the second class. Since the two classes completely overlap it is impossible to have a classifier with zero error. The minimum possible error is known as the Bayes error and

Citation Download Citation

Jeffrey R. Carter and Wayne E. Simon "Statistical learning from nonrecurrent experience with discrete input variables and recursive-error-minimization equations", Proc. SPIE 1294, Applications of Artificial Neural Networks, (1 August 1990); https://doi.org/10.1117/12.21211

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