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
| Τίτλος: | 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 |
|---|---|
| Συγγραφείς: | BURATTINI, ERNESTO, PASCONCINO A., TAMBURRINI, GUGLIELMO |
| Πηγή: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Mathware & soft computing; 1995: Vol.: 2 Núm.: 2 |
| Στοιχεία εκδότη: | Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1995. |
| Έτος έκδοσης: | 1995 |
| Θεματικοί όροι: | 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 |
| Περιγραφή: | 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. |
| Τύπος εγγράφου: | Article |
| Περιγραφή αρχείου: | application/pdf; application/xml; text/html |
| Γλώσσα: | English |
| Σύνδεσμος πρόσβασης: | 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 |
| Αριθμός Καταχώρησης: | edsair.dedup.wf.002..4dc9cf6882c7584a3a706b2eff37a2a2 |
| Βάση Δεδομένων: | OpenAIRE |
| Η περιγραφή δεν είναι διαθέσιμη |