Matches in SemOpenAlex for { <https://semopenalex.org/work/W181107822> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W181107822 abstract "The integration of symbolic prior knowledge and neural networks in so-called Knowledge and neural networks is becoming increasingly popular for solving difficult real-world problems(1). Hybrid intelligent systems that combine and artificial neural network systems typically have four phases involving domain knowledge representation, mapping into connectionist network, network training, and rule extraction respectively. In order to obtain a concise set of symbolic rules, redundant and irrelevant units and connections of a trained neural network are usually removed by a network pruning algorithm before rule are extracted Typical pruning algorithms require retraining the network, which incurs additional cost. In this paper, we introduce a new rule extraction technique without network retraining. Our technique is a universal and comprehensive approach that extracts all embedded knowledge in a trained artificial neural network and represents it in a rule base format. Experimental results show that the size and the predictive accuracy of the rule generated are comparable to those extracted by another method, which prunes and retrains the network." @default.
- W181107822 created "2016-06-24" @default.
- W181107822 creator A5083423975 @default.
- W181107822 creator A5089944570 @default.
- W181107822 date "2004-01-01" @default.
- W181107822 modified "2023-09-26" @default.
- W181107822 title "A HYBRID LEARNING ALGORITHM" @default.
- W181107822 cites W2037537409 @default.
- W181107822 cites W2063046703 @default.
- W181107822 cites W2084812512 @default.
- W181107822 cites W2125389748 @default.
- W181107822 cites W2133671888 @default.
- W181107822 cites W2160699933 @default.
- W181107822 hasPublicationYear "2004" @default.
- W181107822 type Work @default.
- W181107822 sameAs 181107822 @default.
- W181107822 citedByCount "1" @default.
- W181107822 crossrefType "journal-article" @default.
- W181107822 hasAuthorship W181107822A5083423975 @default.
- W181107822 hasAuthorship W181107822A5089944570 @default.
- W181107822 hasConcept C108010975 @default.
- W181107822 hasConcept C11413529 @default.
- W181107822 hasConcept C119857082 @default.
- W181107822 hasConcept C144133560 @default.
- W181107822 hasConcept C154945302 @default.
- W181107822 hasConcept C155202549 @default.
- W181107822 hasConcept C175202392 @default.
- W181107822 hasConcept C177264268 @default.
- W181107822 hasConcept C199360897 @default.
- W181107822 hasConcept C207685749 @default.
- W181107822 hasConcept C2778712577 @default.
- W181107822 hasConcept C41008148 @default.
- W181107822 hasConcept C4554734 @default.
- W181107822 hasConcept C50644808 @default.
- W181107822 hasConcept C6557445 @default.
- W181107822 hasConcept C8521452 @default.
- W181107822 hasConcept C86803240 @default.
- W181107822 hasConceptScore W181107822C108010975 @default.
- W181107822 hasConceptScore W181107822C11413529 @default.
- W181107822 hasConceptScore W181107822C119857082 @default.
- W181107822 hasConceptScore W181107822C144133560 @default.
- W181107822 hasConceptScore W181107822C154945302 @default.
- W181107822 hasConceptScore W181107822C155202549 @default.
- W181107822 hasConceptScore W181107822C175202392 @default.
- W181107822 hasConceptScore W181107822C177264268 @default.
- W181107822 hasConceptScore W181107822C199360897 @default.
- W181107822 hasConceptScore W181107822C207685749 @default.
- W181107822 hasConceptScore W181107822C2778712577 @default.
- W181107822 hasConceptScore W181107822C41008148 @default.
- W181107822 hasConceptScore W181107822C4554734 @default.
- W181107822 hasConceptScore W181107822C50644808 @default.
- W181107822 hasConceptScore W181107822C6557445 @default.
- W181107822 hasConceptScore W181107822C8521452 @default.
- W181107822 hasConceptScore W181107822C86803240 @default.
- W181107822 hasLocation W1811078221 @default.
- W181107822 hasOpenAccess W181107822 @default.
- W181107822 hasPrimaryLocation W1811078221 @default.
- W181107822 hasRelatedWork W1517147305 @default.
- W181107822 hasRelatedWork W1538344016 @default.
- W181107822 hasRelatedWork W1601698119 @default.
- W181107822 hasRelatedWork W1605926639 @default.
- W181107822 hasRelatedWork W1650405992 @default.
- W181107822 hasRelatedWork W1989574962 @default.
- W181107822 hasRelatedWork W2108704760 @default.
- W181107822 hasRelatedWork W2112649152 @default.
- W181107822 hasRelatedWork W2115929981 @default.
- W181107822 hasRelatedWork W2120299300 @default.
- W181107822 hasRelatedWork W2148623873 @default.
- W181107822 hasRelatedWork W2150395249 @default.
- W181107822 hasRelatedWork W2235915642 @default.
- W181107822 hasRelatedWork W2241551256 @default.
- W181107822 hasRelatedWork W2367296909 @default.
- W181107822 hasRelatedWork W2413313105 @default.
- W181107822 hasRelatedWork W2561891060 @default.
- W181107822 hasRelatedWork W2899983622 @default.
- W181107822 hasRelatedWork W3147413282 @default.
- W181107822 hasRelatedWork W2188913041 @default.
- W181107822 isParatext "false" @default.
- W181107822 isRetracted "false" @default.
- W181107822 magId "181107822" @default.
- W181107822 workType "article" @default.