Matches in SemOpenAlex for { <https://semopenalex.org/work/W2183338763> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2183338763 abstract "How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new learning method for pattern recognition, called the incremental backpropagation learning network, which employs bounded weight modification and structural adaptation learning rules and applies initial knowledge to constrain the learning process. The viability of this approach is demonstrated for classification problems including the iris and the promoter domains. N learning system updates its hypotheses as A a new instance arrives without reexamining old instances. In other words, an incremental-learning system learns Y based on X, then learns Z based on Y, and so on. Such a learning strategy is both spatially and temporally economical since it need not store and reprocess old instances. It is especially crucial for a learning system which continually receives input and must process it in a real-time manner. Also, learning based on a single instance has been an important topic in machine learning. At this point, humans appear to learn better than machines from single instances. The backpropagation learning network is not in nature. Suppose it was trained on instance set A and then retrained on set B, its knowledge about set A may be lost. To learn a new instance while keeping old memory, the backpropagation network has to be trained on the new instance along with old instances. In the case of nonstationary data statistics, the network should be adapted to the new instance and preserve previous knowledge if it is not in conflict with that instance. A technique is to minimize the network output error with respect to old instances subject to the approximation of the network output to the desired output of the new instance (ll). This is not an learning technique since old instances should still be reexamined. In this paper, we present a new learning method for pattern recognition, called the backpropagation learning network (IBPLN), which employs bounded weight modification and structural adaptation learning rules. Then experimental results are described." @default.
- W2183338763 created "2016-06-24" @default.
- W2183338763 creator A5019504861 @default.
- W2183338763 creator A5021013165 @default.
- W2183338763 creator A5087583746 @default.
- W2183338763 date "1996-01-01" @default.
- W2183338763 modified "2023-09-26" @default.
- W2183338763 title "Incremental B ackpropagation Learning Networks" @default.
- W2183338763 cites W1489920315 @default.
- W2183338763 cites W2099034483 @default.
- W2183338763 cites W2108233338 @default.
- W2183338763 cites W2142348943 @default.
- W2183338763 cites W2150789422 @default.
- W2183338763 cites W2165758113 @default.
- W2183338763 cites W2169554323 @default.
- W2183338763 cites W2189004000 @default.
- W2183338763 cites W2766736793 @default.
- W2183338763 cites W3207342693 @default.
- W2183338763 hasPublicationYear "1996" @default.
- W2183338763 type Work @default.
- W2183338763 sameAs 2183338763 @default.
- W2183338763 citedByCount "0" @default.
- W2183338763 crossrefType "journal-article" @default.
- W2183338763 hasAuthorship W2183338763A5019504861 @default.
- W2183338763 hasAuthorship W2183338763A5021013165 @default.
- W2183338763 hasAuthorship W2183338763A5087583746 @default.
- W2183338763 hasConcept C108583219 @default.
- W2183338763 hasConcept C111919701 @default.
- W2183338763 hasConcept C119857082 @default.
- W2183338763 hasConcept C138885662 @default.
- W2183338763 hasConcept C154945302 @default.
- W2183338763 hasConcept C155032097 @default.
- W2183338763 hasConcept C177264268 @default.
- W2183338763 hasConcept C199360897 @default.
- W2183338763 hasConcept C24138899 @default.
- W2183338763 hasConcept C26517878 @default.
- W2183338763 hasConcept C38652104 @default.
- W2183338763 hasConcept C40506919 @default.
- W2183338763 hasConcept C41008148 @default.
- W2183338763 hasConcept C41895202 @default.
- W2183338763 hasConcept C50644808 @default.
- W2183338763 hasConcept C7149132 @default.
- W2183338763 hasConcept C77967617 @default.
- W2183338763 hasConcept C98045186 @default.
- W2183338763 hasConceptScore W2183338763C108583219 @default.
- W2183338763 hasConceptScore W2183338763C111919701 @default.
- W2183338763 hasConceptScore W2183338763C119857082 @default.
- W2183338763 hasConceptScore W2183338763C138885662 @default.
- W2183338763 hasConceptScore W2183338763C154945302 @default.
- W2183338763 hasConceptScore W2183338763C155032097 @default.
- W2183338763 hasConceptScore W2183338763C177264268 @default.
- W2183338763 hasConceptScore W2183338763C199360897 @default.
- W2183338763 hasConceptScore W2183338763C24138899 @default.
- W2183338763 hasConceptScore W2183338763C26517878 @default.
- W2183338763 hasConceptScore W2183338763C38652104 @default.
- W2183338763 hasConceptScore W2183338763C40506919 @default.
- W2183338763 hasConceptScore W2183338763C41008148 @default.
- W2183338763 hasConceptScore W2183338763C41895202 @default.
- W2183338763 hasConceptScore W2183338763C50644808 @default.
- W2183338763 hasConceptScore W2183338763C7149132 @default.
- W2183338763 hasConceptScore W2183338763C77967617 @default.
- W2183338763 hasConceptScore W2183338763C98045186 @default.
- W2183338763 hasLocation W21833387631 @default.
- W2183338763 hasOpenAccess W2183338763 @default.
- W2183338763 hasPrimaryLocation W21833387631 @default.
- W2183338763 hasRelatedWork W103132527 @default.
- W2183338763 hasRelatedWork W1507480455 @default.
- W2183338763 hasRelatedWork W1513988862 @default.
- W2183338763 hasRelatedWork W2076683260 @default.
- W2183338763 hasRelatedWork W2120355167 @default.
- W2183338763 hasRelatedWork W2147368400 @default.
- W2183338763 hasRelatedWork W2156938623 @default.
- W2183338763 hasRelatedWork W2233448054 @default.
- W2183338763 hasRelatedWork W2768412495 @default.
- W2183338763 hasRelatedWork W2772691796 @default.
- W2183338763 hasRelatedWork W3002177189 @default.
- W2183338763 hasRelatedWork W3057055245 @default.
- W2183338763 hasRelatedWork W3107564787 @default.
- W2183338763 hasRelatedWork W3135712659 @default.
- W2183338763 hasRelatedWork W3168068006 @default.
- W2183338763 hasRelatedWork W3170588109 @default.
- W2183338763 hasRelatedWork W3174111860 @default.
- W2183338763 hasRelatedWork W3176043281 @default.
- W2183338763 hasRelatedWork W44416870 @default.
- W2183338763 hasRelatedWork W1567037419 @default.
- W2183338763 isParatext "false" @default.
- W2183338763 isRetracted "false" @default.
- W2183338763 magId "2183338763" @default.
- W2183338763 workType "article" @default.