FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2923002339> ?p ?o ?g. }

• W2923002339 endingPage "16" @default.
• W2923002339 startingPage "1" @default.
• W2923002339 abstract "Neuroevolution is the field of study that uses evolutionary computation in order to optimize certain aspect of the design of neural networks, most often its topology and hyperparameters. The field was introduced in the late-1980s, but only in the latest years the field has become mature enough to enable the optimization of deep learning models, such as convolutional neural networks. In this paper, we rely on previous work to apply neuroevolution in order to optimize the topology of deep neural networks that can be used to solve the problem of handwritten character recognition. Moreover, we take advantage of the fact that evolutionary algorithms optimize a population of candidate solutions, by combining a set of the best evolved models resulting in a committee of convolutional neural networks. This process is enhanced by using specific mechanisms to preserve the diversity of the population. Additionally, in this paper, we address one of the disadvantages of neuroevolution: the process is very expensive in terms of computational time. To lessen this issue, we explore the performance of topology transfer learning: whether the best topology obtained using neuroevolution for a certain domain can be successfully applied to a different domain. By doing so, the expensive process of neuroevolution can be reused to tackle different problems, turning it into a more appealing approach for optimizing the design of neural networks topologies. After evaluating our proposal, results show that both the use of neuroevolved committees and the application of topology transfer learning are successful: committees of convolutional neural networks are able to improve classification results when compared to single models, and topologies learned for one problem can be reused for a different problem and data with a good performance. Additionally, both approaches can be combined by building committees of transferred topologies, and this combination attains results that combine the best of both approaches." @default.
• W2923002339 created "2019-04-01" @default.
• W2923002339 creator A5027117264 @default.
• W2923002339 creator A5058638746 @default.
• W2923002339 creator A5069993099 @default.
• W2923002339 date "2019-03-26" @default.
• W2923002339 modified "2023-09-24" @default.
• W2923002339 title "Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning" @default.
• W2923002339 cites W1498436455 @default.
• W2923002339 cites W1987778624 @default.
• W2923002339 cites W2076698365 @default.
• W2923002339 cites W2105023627 @default.
• W2923002339 cites W2112796928 @default.
• W2923002339 cites W2119814172 @default.
• W2923002339 cites W2165698076 @default.
• W2923002339 cites W2559785631 @default.
• W2923002339 cites W2755860313 @default.
• W2923002339 cites W2761692805 @default.
• W2923002339 cites W2776601846 @default.
• W2923002339 cites W2782162974 @default.
• W2923002339 cites W2906697496 @default.
• W2923002339 cites W2963176196 @default.
• W2923002339 doi "https://doi.org/10.1155/2019/2952304" @default.
• W2923002339 hasPublicationYear "2019" @default.
• W2923002339 type Work @default.
• W2923002339 sameAs 2923002339 @default.
• W2923002339 citedByCount "31" @default.
• W2923002339 countsByYear W29230023392019 @default.
• W2923002339 countsByYear W29230023392020 @default.
• W2923002339 countsByYear W29230023392021 @default.
• W2923002339 countsByYear W29230023392022 @default.
• W2923002339 countsByYear W29230023392023 @default.
• W2923002339 crossrefType "journal-article" @default.
• W2923002339 hasAuthorship W2923002339A5027117264 @default.
• W2923002339 hasAuthorship W2923002339A5058638746 @default.
• W2923002339 hasAuthorship W2923002339A5069993099 @default.
• W2923002339 hasBestOaLocation W29230023391 @default.
• W2923002339 hasConcept C105902424 @default.
• W2923002339 hasConcept C108583219 @default.
• W2923002339 hasConcept C111919701 @default.
• W2923002339 hasConcept C114614502 @default.
• W2923002339 hasConcept C118070581 @default.
• W2923002339 hasConcept C119857082 @default.
• W2923002339 hasConcept C134306372 @default.
• W2923002339 hasConcept C144024400 @default.
• W2923002339 hasConcept C149923435 @default.
• W2923002339 hasConcept C150899416 @default.
• W2923002339 hasConcept C154945302 @default.
• W2923002339 hasConcept C159149176 @default.
• W2923002339 hasConcept C175202392 @default.
• W2923002339 hasConcept C184720557 @default.
• W2923002339 hasConcept C199845137 @default.
• W2923002339 hasConcept C202444582 @default.
• W2923002339 hasConcept C2908647359 @default.
• W2923002339 hasConcept C33923547 @default.
• W2923002339 hasConcept C36503486 @default.
• W2923002339 hasConcept C41008148 @default.
• W2923002339 hasConcept C41445625 @default.
• W2923002339 hasConcept C50644808 @default.
• W2923002339 hasConcept C81363708 @default.
• W2923002339 hasConcept C8642999 @default.
• W2923002339 hasConcept C9652623 @default.
• W2923002339 hasConcept C98045186 @default.
• W2923002339 hasConceptScore W2923002339C105902424 @default.
• W2923002339 hasConceptScore W2923002339C108583219 @default.
• W2923002339 hasConceptScore W2923002339C111919701 @default.
• W2923002339 hasConceptScore W2923002339C114614502 @default.
• W2923002339 hasConceptScore W2923002339C118070581 @default.
• W2923002339 hasConceptScore W2923002339C119857082 @default.
• W2923002339 hasConceptScore W2923002339C134306372 @default.
• W2923002339 hasConceptScore W2923002339C144024400 @default.
• W2923002339 hasConceptScore W2923002339C149923435 @default.
• W2923002339 hasConceptScore W2923002339C150899416 @default.
• W2923002339 hasConceptScore W2923002339C154945302 @default.
• W2923002339 hasConceptScore W2923002339C159149176 @default.
• W2923002339 hasConceptScore W2923002339C175202392 @default.
• W2923002339 hasConceptScore W2923002339C184720557 @default.
• W2923002339 hasConceptScore W2923002339C199845137 @default.
• W2923002339 hasConceptScore W2923002339C202444582 @default.
• W2923002339 hasConceptScore W2923002339C2908647359 @default.
• W2923002339 hasConceptScore W2923002339C33923547 @default.
• W2923002339 hasConceptScore W2923002339C36503486 @default.
• W2923002339 hasConceptScore W2923002339C41008148 @default.
• W2923002339 hasConceptScore W2923002339C41445625 @default.
• W2923002339 hasConceptScore W2923002339C50644808 @default.
• W2923002339 hasConceptScore W2923002339C81363708 @default.
• W2923002339 hasConceptScore W2923002339C8642999 @default.
• W2923002339 hasConceptScore W2923002339C9652623 @default.
• W2923002339 hasConceptScore W2923002339C98045186 @default.
• W2923002339 hasFunder F4320321764 @default.
• W2923002339 hasLocation W29230023391 @default.
• W2923002339 hasLocation W29230023392 @default.
• W2923002339 hasOpenAccess W2923002339 @default.
• W2923002339 hasPrimaryLocation W29230023391 @default.
• W2923002339 hasRelatedWork W100361683 @default.
• W2923002339 hasRelatedWork W2923002339 @default.
• W2923002339 hasRelatedWork W3003770199 @default.
• W2923002339 hasRelatedWork W3021430260 @default.

• next