Matches in SemOpenAlex for { <https://semopenalex.org/work/W2734473668> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W2734473668 abstract "Feature Selective Neuroevolution of Augmenting Topologies (FS-NEAT) and Feature De-selective Neuroevolution of Augmenting Topologies (FD-NEAT) are two well-known methods for optimizing the topology and the weights of Artificial Neural Networks (ANNs) while simultaneously performing feature selection. Literature has shown that starting the evolution with ANNs of one hidden layer can affect FD-NEAT's and FS-NEAT's performances. However, no study exists that investigates the effects of changing the networks' initial connectivity. In this paper we investigate how the choice of the number of initially connected inputs affects the performance of FD-NEAT and FS-NEAT in terms of accuracy, number of generations required for convergence, ability of performing feature selection and size of the evolved networks. For this purpose we employ artificial datasets of increasing complexity based on the exclusive-or (XOR) problem with irrelevant features. The different initial topological settings are compared using Kruskal-Wallis hypothesis tests with Bonferroni correction (p" @default.
- W2734473668 created "2017-07-21" @default.
- W2734473668 creator A5004119249 @default.
- W2734473668 creator A5059882142 @default.
- W2734473668 date "2017-07-15" @default.
- W2734473668 modified "2023-10-18" @default.
- W2734473668 title "An investigation of topological choices in FS-NEAT and FD-NEAT on XOR-based problems of increased complexity" @default.
- W2734473668 cites W1970848871 @default.
- W2734473668 cites W201674293 @default.
- W2734473668 cites W2071441967 @default.
- W2734473668 cites W2096232175 @default.
- W2734473668 cites W2100097207 @default.
- W2734473668 cites W2111935653 @default.
- W2734473668 cites W2138784882 @default.
- W2734473668 cites W2162813238 @default.
- W2734473668 cites W2588242161 @default.
- W2734473668 doi "https://doi.org/10.1145/3067695.3082497" @default.
- W2734473668 hasPublicationYear "2017" @default.
- W2734473668 type Work @default.
- W2734473668 sameAs 2734473668 @default.
- W2734473668 citedByCount "6" @default.
- W2734473668 countsByYear W27344736682017 @default.
- W2734473668 countsByYear W27344736682018 @default.
- W2734473668 countsByYear W27344736682019 @default.
- W2734473668 countsByYear W27344736682020 @default.
- W2734473668 countsByYear W27344736682021 @default.
- W2734473668 crossrefType "proceedings-article" @default.
- W2734473668 hasAuthorship W2734473668A5004119249 @default.
- W2734473668 hasAuthorship W2734473668A5059882142 @default.
- W2734473668 hasConcept C114614502 @default.
- W2734473668 hasConcept C184720557 @default.
- W2734473668 hasConcept C33923547 @default.
- W2734473668 hasConcept C41008148 @default.
- W2734473668 hasConcept C80444323 @default.
- W2734473668 hasConceptScore W2734473668C114614502 @default.
- W2734473668 hasConceptScore W2734473668C184720557 @default.
- W2734473668 hasConceptScore W2734473668C33923547 @default.
- W2734473668 hasConceptScore W2734473668C41008148 @default.
- W2734473668 hasConceptScore W2734473668C80444323 @default.
- W2734473668 hasFunder F4320321730 @default.
- W2734473668 hasLocation W27344736681 @default.
- W2734473668 hasOpenAccess W2734473668 @default.
- W2734473668 hasPrimaryLocation W27344736681 @default.
- W2734473668 hasRelatedWork W1974891317 @default.
- W2734473668 hasRelatedWork W2044189972 @default.
- W2734473668 hasRelatedWork W2313400459 @default.
- W2734473668 hasRelatedWork W2392953011 @default.
- W2734473668 hasRelatedWork W2748952813 @default.
- W2734473668 hasRelatedWork W2899084033 @default.
- W2734473668 hasRelatedWork W2913765211 @default.
- W2734473668 hasRelatedWork W2950271745 @default.
- W2734473668 hasRelatedWork W4245490552 @default.
- W2734473668 hasRelatedWork W4288418753 @default.
- W2734473668 isParatext "false" @default.
- W2734473668 isRetracted "false" @default.
- W2734473668 magId "2734473668" @default.
- W2734473668 workType "article" @default.