FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375948379> ?p ?o ?g. }

• W4375948379 endingPage "119031" @default.
• W4375948379 startingPage "119031" @default.
• W4375948379 abstract "The architecture of multilayer perceptron (MLP) neural networks dictates the network's performance. However, aiming at the specific classification problems, suitable architectures of MLPs must be determined beforehand. More often, the design decisions rely on a trial and error learning and the experience knowledge. To automatically design an MLP's network architecture and optimize network parameters, a multiobjective bilevel programming model is built. In this model, a multiobjective optimization problem is constructed in the upper level for obtaining a set of Pareto optimal architectures of the MLPs, considering network complexity, training error rate, and validation error rate, while a single-objective optimization problem is established in the lower level to search for the optimum network parameters for a given network architecture. For dealing with this model efficiently, a novel multiobjective hierarchical learning algorithm (MOHLA) is proposed, in which an integer-coding NSGA-II is developed as the upper-level optimizer for a set of Pareto optimal network structures of the MLPs, while a non-iterative method is regarded as the lower-level solver for the MLPs' connection parameters. After a set of trained MLPs is obtained finally by using MOHLA, a selective ensemble strategy is adopted for improving identification accuracy. Three types of multiobjective bilevel programming models are investigated and compared in the experiments. Moreover, the proposed MOHLA is compared with several state-of-the-art learning approaches on various classification problems. The experimental results confirm that MOHLA performs well." @default.
• W4375948379 created "2023-05-10" @default.
• W4375948379 creator A5010638666 @default.
• W4375948379 creator A5026356470 @default.
• W4375948379 creator A5047167952 @default.
• W4375948379 creator A5056456094 @default.
• W4375948379 date "2023-09-01" @default.
• W4375948379 modified "2023-10-15" @default.
• W4375948379 title "Multiobjective bilevel programming model for multilayer perceptron neural networks" @default.
• W4375948379 cites W1966198712 @default.
• W4375948379 cites W1977398984 @default.
• W4375948379 cites W1982664399 @default.
• W4375948379 cites W1985773453 @default.
• W4375948379 cites W2010941383 @default.
• W4375948379 cites W2012428944 @default.
• W4375948379 cites W2015304908 @default.
• W4375948379 cites W2015432825 @default.
• W4375948379 cites W2021309800 @default.
• W4375948379 cites W2032442397 @default.
• W4375948379 cites W2061119986 @default.
• W4375948379 cites W2062961150 @default.
• W4375948379 cites W2063757130 @default.
• W4375948379 cites W2067878879 @default.
• W4375948379 cites W2071082401 @default.
• W4375948379 cites W2100128988 @default.
• W4375948379 cites W2103457925 @default.
• W4375948379 cites W2111072639 @default.
• W4375948379 cites W2112299196 @default.
• W4375948379 cites W2114053544 @default.
• W4375948379 cites W2126105956 @default.
• W4375948379 cites W2140229565 @default.
• W4375948379 cites W2141695047 @default.
• W4375948379 cites W2143381319 @default.
• W4375948379 cites W2146300243 @default.
• W4375948379 cites W2161205534 @default.
• W4375948379 cites W2193660226 @default.
• W4375948379 cites W2301541953 @default.
• W4375948379 cites W2475253955 @default.
• W4375948379 cites W2553852618 @default.
• W4375948379 cites W2578980197 @default.
• W4375948379 cites W2587345921 @default.
• W4375948379 cites W2753648062 @default.
• W4375948379 cites W2887065738 @default.
• W4375948379 cites W2898721230 @default.
• W4375948379 cites W2907227550 @default.
• W4375948379 cites W2912075857 @default.
• W4375948379 cites W2927272339 @default.
• W4375948379 cites W2947137917 @default.
• W4375948379 cites W2959010962 @default.
• W4375948379 cites W3090931713 @default.
• W4375948379 cites W3103320289 @default.
• W4375948379 cites W4225626756 @default.
• W4375948379 cites W4281974526 @default.
• W4375948379 doi "https://doi.org/10.1016/j.ins.2023.119031" @default.
• W4375948379 hasPublicationYear "2023" @default.
• W4375948379 type Work @default.
• W4375948379 citedByCount "2" @default.
• W4375948379 countsByYear W43759483792023 @default.
• W4375948379 crossrefType "journal-article" @default.
• W4375948379 hasAuthorship W4375948379A5010638666 @default.
• W4375948379 hasAuthorship W4375948379A5026356470 @default.
• W4375948379 hasAuthorship W4375948379A5047167952 @default.
• W4375948379 hasAuthorship W4375948379A5056456094 @default.
• W4375948379 hasConcept C11413529 @default.
• W4375948379 hasConcept C126255220 @default.
• W4375948379 hasConcept C137635306 @default.
• W4375948379 hasConcept C137836250 @default.
• W4375948379 hasConcept C154945302 @default.
• W4375948379 hasConcept C177264268 @default.
• W4375948379 hasConcept C199360897 @default.
• W4375948379 hasConcept C3309286 @default.
• W4375948379 hasConcept C33923547 @default.
• W4375948379 hasConcept C41008148 @default.
• W4375948379 hasConcept C50644808 @default.
• W4375948379 hasConcept C60908668 @default.
• W4375948379 hasConceptScore W4375948379C11413529 @default.
• W4375948379 hasConceptScore W4375948379C126255220 @default.
• W4375948379 hasConceptScore W4375948379C137635306 @default.
• W4375948379 hasConceptScore W4375948379C137836250 @default.
• W4375948379 hasConceptScore W4375948379C154945302 @default.
• W4375948379 hasConceptScore W4375948379C177264268 @default.
• W4375948379 hasConceptScore W4375948379C199360897 @default.
• W4375948379 hasConceptScore W4375948379C3309286 @default.
• W4375948379 hasConceptScore W4375948379C33923547 @default.
• W4375948379 hasConceptScore W4375948379C41008148 @default.
• W4375948379 hasConceptScore W4375948379C50644808 @default.
• W4375948379 hasConceptScore W4375948379C60908668 @default.
• W4375948379 hasFunder F4320321001 @default.
• W4375948379 hasFunder F4320336567 @default.
• W4375948379 hasLocation W43759483791 @default.
• W4375948379 hasOpenAccess W4375948379 @default.
• W4375948379 hasPrimaryLocation W43759483791 @default.
• W4375948379 hasRelatedWork W1536852012 @default.
• W4375948379 hasRelatedWork W1989923016 @default.
• W4375948379 hasRelatedWork W1994436307 @default.
• W4375948379 hasRelatedWork W2340378315 @default.
• W4375948379 hasRelatedWork W2550138382 @default.
• W4375948379 hasRelatedWork W2745612259 @default.

• next