Matches in SemOpenAlex for { <https://semopenalex.org/work/W69746510> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W69746510 endingPage "73" @default.
- W69746510 startingPage "66" @default.
- W69746510 abstract "Neural networks have been largely applied into many real world pattern classification problems. During the training phase, every neural network can suffer from generalization loss caused by overfitting, thereby the process of learning is highly biased. For this work we use Extreme Learning Machine which is an algorithm for training single hidden layer neural networks, and propose a novel swarm-based method for optimizing its weights and improving generalization performance. The algorithm presents the basic Artificial Fish Swarm Algorithm (AFSA) and some features from Differential Evolution (Crossover and Mutation) to improve the quality of the solutions during the search process. The results of the simulations demonstrated good generalization capacity from the best individuals obtained in the training phase.KeywordsNeural NetworksOptimization" @default.
- W69746510 created "2016-06-24" @default.
- W69746510 creator A5025550530 @default.
- W69746510 creator A5029164446 @default.
- W69746510 date "2012-01-01" @default.
- W69746510 modified "2023-09-27" @default.
- W69746510 title "A Modified Artificial Fish Swarm Algorithm for the Optimization of Extreme Learning Machines" @default.
- W69746510 cites W141982089 @default.
- W69746510 cites W1480100634 @default.
- W69746510 cites W1595159159 @default.
- W69746510 cites W2040604977 @default.
- W69746510 cites W2135248726 @default.
- W69746510 doi "https://doi.org/10.1007/978-3-642-33266-1_9" @default.
- W69746510 hasPublicationYear "2012" @default.
- W69746510 type Work @default.
- W69746510 sameAs 69746510 @default.
- W69746510 citedByCount "1" @default.
- W69746510 countsByYear W697465102017 @default.
- W69746510 crossrefType "book-chapter" @default.
- W69746510 hasAuthorship W69746510A5025550530 @default.
- W69746510 hasAuthorship W69746510A5029164446 @default.
- W69746510 hasConcept C111919701 @default.
- W69746510 hasConcept C11413529 @default.
- W69746510 hasConcept C119857082 @default.
- W69746510 hasConcept C122507166 @default.
- W69746510 hasConcept C134306372 @default.
- W69746510 hasConcept C154945302 @default.
- W69746510 hasConcept C177148314 @default.
- W69746510 hasConcept C181335050 @default.
- W69746510 hasConcept C22019652 @default.
- W69746510 hasConcept C2780150128 @default.
- W69746510 hasConcept C33923547 @default.
- W69746510 hasConcept C41008148 @default.
- W69746510 hasConcept C50644808 @default.
- W69746510 hasConcept C74750220 @default.
- W69746510 hasConcept C98045186 @default.
- W69746510 hasConceptScore W69746510C111919701 @default.
- W69746510 hasConceptScore W69746510C11413529 @default.
- W69746510 hasConceptScore W69746510C119857082 @default.
- W69746510 hasConceptScore W69746510C122507166 @default.
- W69746510 hasConceptScore W69746510C134306372 @default.
- W69746510 hasConceptScore W69746510C154945302 @default.
- W69746510 hasConceptScore W69746510C177148314 @default.
- W69746510 hasConceptScore W69746510C181335050 @default.
- W69746510 hasConceptScore W69746510C22019652 @default.
- W69746510 hasConceptScore W69746510C2780150128 @default.
- W69746510 hasConceptScore W69746510C33923547 @default.
- W69746510 hasConceptScore W69746510C41008148 @default.
- W69746510 hasConceptScore W69746510C50644808 @default.
- W69746510 hasConceptScore W69746510C74750220 @default.
- W69746510 hasConceptScore W69746510C98045186 @default.
- W69746510 hasLocation W697465101 @default.
- W69746510 hasOpenAccess W69746510 @default.
- W69746510 hasPrimaryLocation W697465101 @default.
- W69746510 hasRelatedWork W1597186980 @default.
- W69746510 hasRelatedWork W1999024143 @default.
- W69746510 hasRelatedWork W2029522843 @default.
- W69746510 hasRelatedWork W2032681806 @default.
- W69746510 hasRelatedWork W2035993738 @default.
- W69746510 hasRelatedWork W2059992053 @default.
- W69746510 hasRelatedWork W2067100891 @default.
- W69746510 hasRelatedWork W2146239616 @default.
- W69746510 hasRelatedWork W2163166720 @default.
- W69746510 hasRelatedWork W2168294619 @default.
- W69746510 hasRelatedWork W2545586689 @default.
- W69746510 hasRelatedWork W2554090223 @default.
- W69746510 hasRelatedWork W2795569439 @default.
- W69746510 hasRelatedWork W2810449520 @default.
- W69746510 hasRelatedWork W2918647911 @default.
- W69746510 hasRelatedWork W2978475941 @default.
- W69746510 hasRelatedWork W3003722371 @default.
- W69746510 hasRelatedWork W3101469945 @default.
- W69746510 hasRelatedWork W3162225438 @default.
- W69746510 hasRelatedWork W3176900572 @default.
- W69746510 isParatext "false" @default.
- W69746510 isRetracted "false" @default.
- W69746510 magId "69746510" @default.
- W69746510 workType "book-chapter" @default.