Matches in SemOpenAlex for { <https://semopenalex.org/work/W2300360787> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2300360787 endingPage "384" @default.
- W2300360787 startingPage "368" @default.
- W2300360787 abstract "This paper proposes a hybrid neuro-evolutive algorithm (NEA) that uses a compact indirect encoding scheme (IES) for representing its genotypes (a set of ten production rules of a Lindenmayer System with memory), moreover has the ability to reuse the genotypes and automatically build modular, hierarchical and recurrent neural networks. A genetic algorithm (GA) evolves a Lindenmayer System (L-System) that is used to design the neural network’s architecture. This basic neural codification confers scalability and search space reduction in relation to other methods. Furthermore, the system uses a parallel genome scan engine that increases both the implicit parallelism and convergence of the GA. The fitness function of the NEA rewards economical artificial neural networks (ANNs) that are easily implemented. The NEA was tested on five real-world classification datasets and three well-known datasets for time series forecasting (TSF). The results are statistically compared against established state-of-the-art algorithms and various forecasting methods (ADANN, ARIMA, UCM, and Forecast Pro). In most cases, our NEA outperformed the other methods, delivering the most accurate classification and time series forecasting with the least computational effort. These superior results are attributed to the improved effectiveness and efficiency of NEA in the decision-making process. The result is an optimized neural network architecture for solving classification problems and simulating dynamical systems." @default.
- W2300360787 created "2016-06-24" @default.
- W2300360787 creator A5047066285 @default.
- W2300360787 creator A5090517396 @default.
- W2300360787 creator A5091285556 @default.
- W2300360787 date "2016-09-01" @default.
- W2300360787 modified "2023-09-26" @default.
- W2300360787 title "Optimization of neural networks through grammatical evolution and a genetic algorithm" @default.
- W2300360787 cites W1490180010 @default.
- W2300360787 cites W1964153772 @default.
- W2300360787 cites W1964646852 @default.
- W2300360787 cites W1966991711 @default.
- W2300360787 cites W1971676152 @default.
- W2300360787 cites W1977310618 @default.
- W2300360787 cites W1982388409 @default.
- W2300360787 cites W1994530228 @default.
- W2300360787 cites W2010459589 @default.
- W2300360787 cites W2012391952 @default.
- W2300360787 cites W2016923883 @default.
- W2300360787 cites W2023448113 @default.
- W2300360787 cites W2028967620 @default.
- W2300360787 cites W2031518108 @default.
- W2300360787 cites W2047408307 @default.
- W2300360787 cites W2050870241 @default.
- W2300360787 cites W2072782187 @default.
- W2300360787 cites W2111935653 @default.
- W2300360787 cites W2119814172 @default.
- W2300360787 cites W2126137228 @default.
- W2300360787 cites W2136848732 @default.
- W2300360787 cites W2138321920 @default.
- W2300360787 cites W2144644840 @default.
- W2300360787 cites W2153684665 @default.
- W2300360787 cites W2165132362 @default.
- W2300360787 doi "https://doi.org/10.1016/j.eswa.2016.03.012" @default.
- W2300360787 hasPublicationYear "2016" @default.
- W2300360787 type Work @default.
- W2300360787 sameAs 2300360787 @default.
- W2300360787 citedByCount "28" @default.
- W2300360787 countsByYear W23003607872016 @default.
- W2300360787 countsByYear W23003607872017 @default.
- W2300360787 countsByYear W23003607872018 @default.
- W2300360787 countsByYear W23003607872019 @default.
- W2300360787 countsByYear W23003607872021 @default.
- W2300360787 countsByYear W23003607872022 @default.
- W2300360787 countsByYear W23003607872023 @default.
- W2300360787 crossrefType "journal-article" @default.
- W2300360787 hasAuthorship W2300360787A5047066285 @default.
- W2300360787 hasAuthorship W2300360787A5090517396 @default.
- W2300360787 hasAuthorship W2300360787A5091285556 @default.
- W2300360787 hasConcept C11413529 @default.
- W2300360787 hasConcept C119857082 @default.
- W2300360787 hasConcept C154945302 @default.
- W2300360787 hasConcept C162324750 @default.
- W2300360787 hasConcept C2777303404 @default.
- W2300360787 hasConcept C41008148 @default.
- W2300360787 hasConcept C48044578 @default.
- W2300360787 hasConcept C50522688 @default.
- W2300360787 hasConcept C50644808 @default.
- W2300360787 hasConcept C77088390 @default.
- W2300360787 hasConcept C8880873 @default.
- W2300360787 hasConceptScore W2300360787C11413529 @default.
- W2300360787 hasConceptScore W2300360787C119857082 @default.
- W2300360787 hasConceptScore W2300360787C154945302 @default.
- W2300360787 hasConceptScore W2300360787C162324750 @default.
- W2300360787 hasConceptScore W2300360787C2777303404 @default.
- W2300360787 hasConceptScore W2300360787C41008148 @default.
- W2300360787 hasConceptScore W2300360787C48044578 @default.
- W2300360787 hasConceptScore W2300360787C50522688 @default.
- W2300360787 hasConceptScore W2300360787C50644808 @default.
- W2300360787 hasConceptScore W2300360787C77088390 @default.
- W2300360787 hasConceptScore W2300360787C8880873 @default.
- W2300360787 hasLocation W23003607871 @default.
- W2300360787 hasOpenAccess W2300360787 @default.
- W2300360787 hasPrimaryLocation W23003607871 @default.
- W2300360787 hasRelatedWork W1583013743 @default.
- W2300360787 hasRelatedWork W2054770551 @default.
- W2300360787 hasRelatedWork W2356755074 @default.
- W2300360787 hasRelatedWork W2359549665 @default.
- W2300360787 hasRelatedWork W2371602754 @default.
- W2300360787 hasRelatedWork W2380955682 @default.
- W2300360787 hasRelatedWork W2382761789 @default.
- W2300360787 hasRelatedWork W2392110728 @default.
- W2300360787 hasRelatedWork W4225307033 @default.
- W2300360787 hasRelatedWork W1629725936 @default.
- W2300360787 hasVolume "56" @default.
- W2300360787 isParatext "false" @default.
- W2300360787 isRetracted "false" @default.
- W2300360787 magId "2300360787" @default.
- W2300360787 workType "article" @default.