FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2015304908> ?p ?o ?g. }

• W2015304908 endingPage "1462" @default.
• W2015304908 startingPage "1448" @default.
• W2015304908 abstract "In this paper, we propose a novel technique for the automatic design of Artificial Neural Networks (ANNs) by evolving to the optimal network configuration(s) within an architecture space. It is entirely based on a multi-dimensional Particle Swarm Optimization (MD PSO) technique, which re-forms the native structure of swarm particles in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Therefore, in a multidimensional search space where the optimum dimension is unknown, swarm particles can seek both positional and dimensional optima. This eventually removes the necessity of setting a fixed dimension a priori, which is a common drawback for the family of swarm optimizers. With the proper encoding of the network configurations and parameters into particles, MD PSO can then seek the positional optimum in the error space and the dimensional optimum in the architecture space. The optimum dimension converged at the end of a MD PSO process corresponds to a unique ANN configuration where the network parameters (connections, weights and biases) can then be resolved from the positional optimum reached on that dimension. In addition to this, the proposed technique generates a ranked list of network configurations, from the best to the worst. This is indeed a crucial piece of information, indicating what potential configurations can be alternatives to the best one, and which configurations should not be used at all for a particular problem. In this study, the architecture space is defined over feed-forward, fully-connected ANNs so as to use the conventional techniques such as back-propagation and some other evolutionary methods in this field. The proposed technique is applied over the most challenging synthetic problems to test its optimality on evolving networks and over the benchmark problems to test its generalization capability as well as to make comparative evaluations with the several competing techniques. The experimental results show that the MD PSO evolves to optimum or near-optimum networks in general and has a superior generalization capability. Furthermore, the MD PSO naturally favors a low-dimension solution when it exhibits a competitive performance with a high dimension counterpart and such a native tendency eventually yields the evolution process to the compact network configurations in the architecture space rather than the complex ones, as long as the optimality prevails." @default.
• W2015304908 created "2016-06-24" @default.
• W2015304908 creator A5007583477 @default.
• W2015304908 creator A5047979812 @default.
• W2015304908 creator A5072719292 @default.
• W2015304908 creator A5090636507 @default.
• W2015304908 date "2009-12-01" @default.
• W2015304908 modified "2023-09-26" @default.
• W2015304908 title "Evolutionary artificial neural networks by multi-dimensional particle swarm optimization" @default.
• W2015304908 cites W1552866645 @default.
• W2015304908 cites W1888884532 @default.
• W2015304908 cites W1907706552 @default.
• W2015304908 cites W1948668094 @default.
• W2015304908 cites W1989644846 @default.
• W2015304908 cites W1995341919 @default.
• W2015304908 cites W2020009149 @default.
• W2015304908 cites W2020754962 @default.
• W2015304908 cites W2051680981 @default.
• W2015304908 cites W2053268667 @default.
• W2015304908 cites W2056364562 @default.
• W2015304908 cites W2082610078 @default.
• W2015304908 cites W2103575890 @default.
• W2015304908 cites W2124290836 @default.
• W2015304908 cites W2126857035 @default.
• W2015304908 cites W2128033389 @default.
• W2015304908 cites W2134514463 @default.
• W2015304908 cites W2137699621 @default.
• W2015304908 cites W2138784882 @default.
• W2015304908 cites W2145085734 @default.
• W2015304908 cites W2152195021 @default.
• W2015304908 cites W2158242120 @default.
• W2015304908 cites W2163655817 @default.
• W2015304908 cites W2165132362 @default.
• W2015304908 cites W2165299997 @default.
• W2015304908 cites W4239723685 @default.
• W2015304908 doi "https://doi.org/10.1016/j.neunet.2009.05.013" @default.
• W2015304908 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/19556105" @default.
• W2015304908 hasPublicationYear "2009" @default.
• W2015304908 type Work @default.
• W2015304908 sameAs 2015304908 @default.
• W2015304908 citedByCount "234" @default.
• W2015304908 countsByYear W20153049082012 @default.
• W2015304908 countsByYear W20153049082013 @default.
• W2015304908 countsByYear W20153049082014 @default.
• W2015304908 countsByYear W20153049082015 @default.
• W2015304908 countsByYear W20153049082016 @default.
• W2015304908 countsByYear W20153049082017 @default.
• W2015304908 countsByYear W20153049082018 @default.
• W2015304908 countsByYear W20153049082019 @default.
• W2015304908 countsByYear W20153049082020 @default.
• W2015304908 countsByYear W20153049082021 @default.
• W2015304908 countsByYear W20153049082022 @default.
• W2015304908 countsByYear W20153049082023 @default.
• W2015304908 crossrefType "journal-article" @default.
• W2015304908 hasAuthorship W2015304908A5007583477 @default.
• W2015304908 hasAuthorship W2015304908A5047979812 @default.
• W2015304908 hasAuthorship W2015304908A5072719292 @default.
• W2015304908 hasAuthorship W2015304908A5090636507 @default.
• W2015304908 hasConcept C111472728 @default.
• W2015304908 hasConcept C111919701 @default.
• W2015304908 hasConcept C11413529 @default.
• W2015304908 hasConcept C126255220 @default.
• W2015304908 hasConcept C138885662 @default.
• W2015304908 hasConcept C141934464 @default.
• W2015304908 hasConcept C154945302 @default.
• W2015304908 hasConcept C181335050 @default.
• W2015304908 hasConcept C202444582 @default.
• W2015304908 hasConcept C2778572836 @default.
• W2015304908 hasConcept C33676613 @default.
• W2015304908 hasConcept C33923547 @default.
• W2015304908 hasConcept C41008148 @default.
• W2015304908 hasConcept C50644808 @default.
• W2015304908 hasConcept C75553542 @default.
• W2015304908 hasConcept C85617194 @default.
• W2015304908 hasConcept C98045186 @default.
• W2015304908 hasConceptScore W2015304908C111472728 @default.
• W2015304908 hasConceptScore W2015304908C111919701 @default.
• W2015304908 hasConceptScore W2015304908C11413529 @default.
• W2015304908 hasConceptScore W2015304908C126255220 @default.
• W2015304908 hasConceptScore W2015304908C138885662 @default.
• W2015304908 hasConceptScore W2015304908C141934464 @default.
• W2015304908 hasConceptScore W2015304908C154945302 @default.
• W2015304908 hasConceptScore W2015304908C181335050 @default.
• W2015304908 hasConceptScore W2015304908C202444582 @default.
• W2015304908 hasConceptScore W2015304908C2778572836 @default.
• W2015304908 hasConceptScore W2015304908C33676613 @default.
• W2015304908 hasConceptScore W2015304908C33923547 @default.
• W2015304908 hasConceptScore W2015304908C41008148 @default.
• W2015304908 hasConceptScore W2015304908C50644808 @default.
• W2015304908 hasConceptScore W2015304908C75553542 @default.
• W2015304908 hasConceptScore W2015304908C85617194 @default.
• W2015304908 hasConceptScore W2015304908C98045186 @default.
• W2015304908 hasIssue "10" @default.
• W2015304908 hasLocation W20153049081 @default.
• W2015304908 hasLocation W20153049082 @default.
• W2015304908 hasOpenAccess W2015304908 @default.
• W2015304908 hasPrimaryLocation W20153049081 @default.
• W2015304908 hasRelatedWork W1975627211 @default.

• next