Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published July 1991 | Published
Book Section - Chapter Open

Incremental learning with rule-based neural networks

Abstract

A classifier for discrete-valued variable classification problems is presented. The system utilizes an information-theoretic algorithm for constructing informative rules from example data. These rules are then used to construct a neural network to perform parallel inference and posterior probability estimation. The network can be grown incrementally, so that new data can be incorporated without repeating the training on previous data. It is shown that this technique performs as well as other techniques such as backpropagation while having unique advantages in incremental learning capability, training efficiency, knowledge representation, and hardware implementation suitability.

Additional Information

© 1991 IEEE. This work was supported in part by the Army Research Office under contract number DAAL03-89-K-0126, and in part by DARPA under contract number AFOSR-90-0199.

Attached Files

Published - 00155294.pdf

Files

00155294.pdf
Files (298.6 kB)
Name Size Download all
md5:af1bd00d83f81cca426c840e73a29397
298.6 kB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 20, 2023