Matches in SemOpenAlex for { <https://semopenalex.org/work/W2120355167> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2120355167 abstract "Incremental learning methods usually face the problem of forgetting. To avoid the problem, the system usually needs to re-learn old instances again. During the learning phase, we cannot make the system recognize new inputs. In contrast, k-nearest neighbors (k-NN) memorize new instances only by appending the new instances to its database so that k-NN does not waste learning time. However, k-NN wastes a large amount of resources to record all instances. To solve the problem, the author presents several model-based incremental learning systems for function approximation. Those methods reduce apparent learning time by introducing a sleep phase. Therefore, during the awake phase, the system can recognize known instances and memorize unknown new instances simultaneously. On the other hand, during sleep phase, the system realizes model-selection for reduction of redundant hidden units. This paper presents an extended version of the previous method to improve its generalization ability in addition to applying it to various classification problem. Several benchmark tests show that the new system learns instances quickly, as does k-NN, but uses only about 10% to 50% of the resources of k-NN. The generalization ability also outperforms the k-NN." @default.
- W2120355167 created "2016-06-24" @default.
- W2120355167 creator A5072900555 @default.
- W2120355167 date "2004-06-22" @default.
- W2120355167 modified "2023-09-26" @default.
- W2120355167 title "Incremental learning with sleep-application for predicting posterior distribution" @default.
- W2120355167 cites W1509404520 @default.
- W2120355167 cites W1984049995 @default.
- W2120355167 cites W2108011034 @default.
- W2120355167 cites W2114865067 @default.
- W2120355167 cites W2153291899 @default.
- W2120355167 cites W3139961556 @default.
- W2120355167 doi "https://doi.org/10.1109/ijcnn.2003.1224007" @default.
- W2120355167 hasPublicationYear "2004" @default.
- W2120355167 type Work @default.
- W2120355167 sameAs 2120355167 @default.
- W2120355167 citedByCount "1" @default.
- W2120355167 crossrefType "proceedings-article" @default.
- W2120355167 hasAuthorship W2120355167A5072900555 @default.
- W2120355167 hasConcept C111335779 @default.
- W2120355167 hasConcept C119857082 @default.
- W2120355167 hasConcept C13280743 @default.
- W2120355167 hasConcept C134306372 @default.
- W2120355167 hasConcept C138885662 @default.
- W2120355167 hasConcept C14036430 @default.
- W2120355167 hasConcept C145420912 @default.
- W2120355167 hasConcept C154945302 @default.
- W2120355167 hasConcept C177148314 @default.
- W2120355167 hasConcept C185798385 @default.
- W2120355167 hasConcept C205649164 @default.
- W2120355167 hasConcept C24138899 @default.
- W2120355167 hasConcept C2524010 @default.
- W2120355167 hasConcept C30038468 @default.
- W2120355167 hasConcept C33923547 @default.
- W2120355167 hasConcept C41008148 @default.
- W2120355167 hasConcept C41895202 @default.
- W2120355167 hasConcept C7149132 @default.
- W2120355167 hasConcept C78458016 @default.
- W2120355167 hasConcept C8038995 @default.
- W2120355167 hasConcept C86803240 @default.
- W2120355167 hasConceptScore W2120355167C111335779 @default.
- W2120355167 hasConceptScore W2120355167C119857082 @default.
- W2120355167 hasConceptScore W2120355167C13280743 @default.
- W2120355167 hasConceptScore W2120355167C134306372 @default.
- W2120355167 hasConceptScore W2120355167C138885662 @default.
- W2120355167 hasConceptScore W2120355167C14036430 @default.
- W2120355167 hasConceptScore W2120355167C145420912 @default.
- W2120355167 hasConceptScore W2120355167C154945302 @default.
- W2120355167 hasConceptScore W2120355167C177148314 @default.
- W2120355167 hasConceptScore W2120355167C185798385 @default.
- W2120355167 hasConceptScore W2120355167C205649164 @default.
- W2120355167 hasConceptScore W2120355167C24138899 @default.
- W2120355167 hasConceptScore W2120355167C2524010 @default.
- W2120355167 hasConceptScore W2120355167C30038468 @default.
- W2120355167 hasConceptScore W2120355167C33923547 @default.
- W2120355167 hasConceptScore W2120355167C41008148 @default.
- W2120355167 hasConceptScore W2120355167C41895202 @default.
- W2120355167 hasConceptScore W2120355167C7149132 @default.
- W2120355167 hasConceptScore W2120355167C78458016 @default.
- W2120355167 hasConceptScore W2120355167C8038995 @default.
- W2120355167 hasConceptScore W2120355167C86803240 @default.
- W2120355167 hasLocation W21203551671 @default.
- W2120355167 hasOpenAccess W2120355167 @default.
- W2120355167 hasPrimaryLocation W21203551671 @default.
- W2120355167 hasRelatedWork W1487472306 @default.
- W2120355167 hasRelatedWork W1523542129 @default.
- W2120355167 hasRelatedWork W1535494315 @default.
- W2120355167 hasRelatedWork W2054544941 @default.
- W2120355167 hasRelatedWork W2058672592 @default.
- W2120355167 hasRelatedWork W2122702557 @default.
- W2120355167 hasRelatedWork W2124434282 @default.
- W2120355167 hasRelatedWork W2147368400 @default.
- W2120355167 hasRelatedWork W2183338763 @default.
- W2120355167 hasRelatedWork W2805228670 @default.
- W2120355167 hasRelatedWork W2850509156 @default.
- W2120355167 hasRelatedWork W2972740417 @default.
- W2120355167 hasRelatedWork W2998073605 @default.
- W2120355167 hasRelatedWork W3002177189 @default.
- W2120355167 hasRelatedWork W3057055245 @default.
- W2120355167 hasRelatedWork W3112858938 @default.
- W2120355167 hasRelatedWork W3168068006 @default.
- W2120355167 hasRelatedWork W3170588109 @default.
- W2120355167 hasRelatedWork W3173493671 @default.
- W2120355167 hasRelatedWork W55558254 @default.
- W2120355167 isParatext "false" @default.
- W2120355167 isRetracted "false" @default.
- W2120355167 magId "2120355167" @default.
- W2120355167 workType "article" @default.