Academic Journal

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

Bibliographic Details
Title: A chunking mechanism in a neural system for the parallel processing of a propositional production rules: A chunking mechanism in a neural system for the parallel processing of propositional production rules
Authors: BURATTINI, ERNESTO, PASCONCINO A., TAMBURRINI, GUGLIELMO
Source: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Mathware & soft computing; 1995: Vol.: 2 Núm.: 2
Publisher Information: Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1995.
Publication Year: 1995
Subject Terms: Neural systems, 05 social sciences, Learning and adaptive systems in artificial intelligence, 02 engineering and technology, Rule-based knowledge, Chunking mechanism, 68 Computer science::68Q Theory of computing [Classificació AMS], Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence, rule-based knowledge base, learning algorithm, Classificació AMS::68 Computer science::68Q Theory of computing, 0202 electrical engineering, electronic engineering, information engineering, Xarxes neuronals (Informàtica), 0501 psychology and cognitive sciences
Description: 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.
Document Type: Article
File Description: application/pdf; application/xml; text/html
Language: English
Access URL: http://hdl.handle.net/2099/2466
https://hdl.handle.net/2099/2466
https://zbmath.org/951674
http://hdl.handle.net/11588/132242
https://hdl.handle.net/11588/132242
http://www.raco.cat/index.php/Mathware/article/view/84646
Rights: CC BY NC ND
Accession Number: edsair.dedup.wf.002..4dc9cf6882c7584a3a706b2eff37a2a2
Database: OpenAIRE
Be the first to leave a comment!
You must be logged in first