A chunking mechanism in a neural system for the parallel processing of propositional production rules.

Burattini, Ernesto, Pasconcino, A., and Tamburrini, Guglielmo. "A chunking mechanism in a neural system for the parallel processing of propositional production rules.." Mathware and Soft Computing 2.2 (1995): 85-116. <http://eudml.org/doc/39053>.

@article{Burattini1995,
abstract = {The problem of extracting more compact rules from a rule-based knowledge base is approached by means of a chunking mechanism implemented via a neural system. Taking advantage of the parallel processing potentialities of neural systems, the computational problem normally arising when introducing chuncking processes is overcome. Also the memory saturation effect is coped with using some sort of forgetting mechanism which allows the system to eliminate previously stored, but less often used chunks. Even though some connection weights are changed in the process of storing or discarding chunks, we emphasize that this neural system cannot be regarded as a connectionist system, since a localist semantic interpretation is adopted and no classical learning algorithm is employed.},
author = {Burattini, Ernesto, Pasconcino, A., Tamburrini, Guglielmo},
journal = {Mathware and Soft Computing},
keywords = {Inteligencia artificial; Teoría del aprendizaje; Sistemas neuronales; rule-based knowledge base; learning algorithm},
language = {eng},
number = {2},
pages = {85-116},
title = {A chunking mechanism in a neural system for the parallel processing of propositional production rules.},
url = {http://eudml.org/doc/39053},
volume = {2},
year = {1995},
}

TY - JOUR
AU - Burattini, Ernesto
AU - Pasconcino, A.
AU - Tamburrini, Guglielmo
TI - A chunking mechanism in a neural system for the parallel processing of propositional production rules.
JO - Mathware and Soft Computing
PY - 1995
VL - 2
IS - 2
SP - 85
EP - 116
AB - The problem of extracting more compact rules from a rule-based knowledge base is approached by means of a chunking mechanism implemented via a neural system. Taking advantage of the parallel processing potentialities of neural systems, the computational problem normally arising when introducing chuncking processes is overcome. Also the memory saturation effect is coped with using some sort of forgetting mechanism which allows the system to eliminate previously stored, but less often used chunks. Even though some connection weights are changed in the process of storing or discarding chunks, we emphasize that this neural system cannot be regarded as a connectionist system, since a localist semantic interpretation is adopted and no classical learning algorithm is employed.
LA - eng
KW - Inteligencia artificial; Teoría del aprendizaje; Sistemas neuronales; rule-based knowledge base; learning algorithm
UR - http://eudml.org/doc/39053
ER -