1 July 1992 Alternative method for the connectionist learning of k-DNF expressions
Author Affiliations +
Proceedings Volume 1710, Science of Artificial Neural Networks; (1992); doi: 10.1117/12.140102
Event: Aerospace Sensing, 1992, Orlando, FL, United States
Abstract
We show that the extremely long learning times imposed upon connectionist systems by the use of general learning methods such as back propagation and simulated annealing can be drastically shortened by the use of methods geared toward the problem at hand. In particular, the learning of k-DNF expressions is analyzed and a new, more efficient, algorithm is proposed.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas Bitterman, "Alternative method for the connectionist learning of k-DNF expressions", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140102; https://doi.org/10.1117/12.140102
PROCEEDINGS
6 PAGES


SHARE
KEYWORDS
Algorithms

Artificial neural networks

Neural networks

Evolutionary algorithms

Statistical modeling

Chemical analysis

Computer science

Back to Top