Matches in SemOpenAlex for { <https://semopenalex.org/work/W1910079862> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1910079862 abstract "Artificial neural network (ANN) has wide applications such as data processing and classification. However, comparing with other classification methods, ANN needs enormous memory space and training time to build the model. This makes ANN infeasible in practical applications. In this paper, we try to integrate the ideas of human learning mechanism with the existing models of ANN. We propose an incremental neural network construction framework for unsupervised learning. In this framework, a neural network is incrementally constructed by the corresponding subnets with individual instances. First, a subnet maps the relation between inputs and outputs for an observed instance. Then, when combining multiple subnets, the neural network keeps the corresponding abilities to generate the same outputs with the same inputs. This makes the learning process unsupervised and inherent in this framework. In our experiment, Reuters-21578 was used as the dataset to show the effectiveness of the proposed method on text classification. The experimental results showed that our method can effectively classify texts with the best F1-measure of 92.5%. It also showed the learning algorithm can enhance the accuracy effectively and efficiently. This framework also validates scalability in terms of the network size, in which the training and testing times both showed a constant trend. This also validates the feasibility of the method for practical uses. All Rights Reserved © 2015 Universidad Nacional Autonoma de Mexico, Centro de Ciencias Aplicadas y Desarrollo Tecnologico. This is an open access item distributed under the Creative Commons CC License BY-NC-ND 4.0." @default.
- W1910079862 created "2016-06-24" @default.
- W1910079862 creator A5008534258 @default.
- W1910079862 creator A5034485889 @default.
- W1910079862 creator A5037910108 @default.
- W1910079862 creator A5076845353 @default.
- W1910079862 date "2015-04-01" @default.
- W1910079862 modified "2023-09-23" @default.
- W1910079862 title "A constructive algorithm for unsupervised learning with incremental neural network" @default.
- W1910079862 cites W1498436455 @default.
- W1910079862 cites W1575784870 @default.
- W1910079862 cites W2052649282 @default.
- W1910079862 cites W2094934653 @default.
- W1910079862 cites W2119466907 @default.
- W1910079862 cites W2120250216 @default.
- W1910079862 cites W2137540340 @default.
- W1910079862 cites W2159129034 @default.
- W1910079862 cites W2163224430 @default.
- W1910079862 cites W4243291825 @default.
- W1910079862 doi "https://doi.org/10.1016/j.jart.2015.06.017" @default.
- W1910079862 hasPublicationYear "2015" @default.
- W1910079862 type Work @default.
- W1910079862 sameAs 1910079862 @default.
- W1910079862 citedByCount "7" @default.
- W1910079862 countsByYear W19100798622016 @default.
- W1910079862 countsByYear W19100798622017 @default.
- W1910079862 countsByYear W19100798622018 @default.
- W1910079862 countsByYear W19100798622019 @default.
- W1910079862 countsByYear W19100798622020 @default.
- W1910079862 crossrefType "journal-article" @default.
- W1910079862 hasAuthorship W1910079862A5008534258 @default.
- W1910079862 hasAuthorship W1910079862A5034485889 @default.
- W1910079862 hasAuthorship W1910079862A5037910108 @default.
- W1910079862 hasAuthorship W1910079862A5076845353 @default.
- W1910079862 hasBestOaLocation W19100798621 @default.
- W1910079862 hasConcept C111919701 @default.
- W1910079862 hasConcept C119857082 @default.
- W1910079862 hasConcept C120822770 @default.
- W1910079862 hasConcept C124101348 @default.
- W1910079862 hasConcept C154945302 @default.
- W1910079862 hasConcept C21099817 @default.
- W1910079862 hasConcept C25343380 @default.
- W1910079862 hasConcept C2778701210 @default.
- W1910079862 hasConcept C31258907 @default.
- W1910079862 hasConcept C41008148 @default.
- W1910079862 hasConcept C48044578 @default.
- W1910079862 hasConcept C50644808 @default.
- W1910079862 hasConcept C77088390 @default.
- W1910079862 hasConcept C8038995 @default.
- W1910079862 hasConcept C98045186 @default.
- W1910079862 hasConceptScore W1910079862C111919701 @default.
- W1910079862 hasConceptScore W1910079862C119857082 @default.
- W1910079862 hasConceptScore W1910079862C120822770 @default.
- W1910079862 hasConceptScore W1910079862C124101348 @default.
- W1910079862 hasConceptScore W1910079862C154945302 @default.
- W1910079862 hasConceptScore W1910079862C21099817 @default.
- W1910079862 hasConceptScore W1910079862C25343380 @default.
- W1910079862 hasConceptScore W1910079862C2778701210 @default.
- W1910079862 hasConceptScore W1910079862C31258907 @default.
- W1910079862 hasConceptScore W1910079862C41008148 @default.
- W1910079862 hasConceptScore W1910079862C48044578 @default.
- W1910079862 hasConceptScore W1910079862C50644808 @default.
- W1910079862 hasConceptScore W1910079862C77088390 @default.
- W1910079862 hasConceptScore W1910079862C8038995 @default.
- W1910079862 hasConceptScore W1910079862C98045186 @default.
- W1910079862 hasLocation W19100798621 @default.
- W1910079862 hasOpenAccess W1910079862 @default.
- W1910079862 hasPrimaryLocation W19100798621 @default.
- W1910079862 hasRelatedWork W1678611306 @default.
- W1910079862 hasRelatedWork W2001603867 @default.
- W1910079862 hasRelatedWork W2015319504 @default.
- W1910079862 hasRelatedWork W2046444225 @default.
- W1910079862 hasRelatedWork W2055221285 @default.
- W1910079862 hasRelatedWork W2062647093 @default.
- W1910079862 hasRelatedWork W2092665724 @default.
- W1910079862 hasRelatedWork W2094236087 @default.
- W1910079862 hasRelatedWork W2098981346 @default.
- W1910079862 hasRelatedWork W2120299300 @default.
- W1910079862 hasRelatedWork W2122946761 @default.
- W1910079862 hasRelatedWork W2127188411 @default.
- W1910079862 hasRelatedWork W2133377210 @default.
- W1910079862 hasRelatedWork W2147944429 @default.
- W1910079862 hasRelatedWork W2162181211 @default.
- W1910079862 hasRelatedWork W2535918113 @default.
- W1910079862 hasRelatedWork W2774611252 @default.
- W1910079862 hasRelatedWork W2974790478 @default.
- W1910079862 hasRelatedWork W3147413282 @default.
- W1910079862 hasRelatedWork W1966635105 @default.
- W1910079862 isParatext "false" @default.
- W1910079862 isRetracted "false" @default.
- W1910079862 magId "1910079862" @default.
- W1910079862 workType "article" @default.