FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1738803388> ?p ?o ?g. }

• W1738803388 abstract "A general problem in model selection is to obtain the right parameters that make a model fit observed data. For a multilayer perceptron (MLP) trained with backpropagation (BP), this means finding the right hidden layer size, appropriate initial weights and learning parameters. The paper proposes a method (G-Prop-II) that attempts to solve that problem by combining a genetic algorithm (GA) and BP to train MLPs with a single hidden layer. The GA selects the initial weights and the learning rate of the network, and changes the number of neurons in the hidden layer through the application of specific genetic operators. G-Prop-II combines the advantages of the global search performed by the GA over the MLP parameter space and the local search of the BP algorithm. The application of the G-Prop-II algorithm to several real world and benchmark problems shows that MLPs evolved using G-Prop-II are smaller and achieve a higher level of generalization than other perceptron training algorithms, such as QuickPropagation or RPROP, and other evolutive algorithms, such as G-LVQ. It also shows some improvement over previous versions of the algorithm." @default.
• W1738803388 created "2016-06-24" @default.
• W1738803388 creator A5001935513 @default.
• W1738803388 creator A5023015655 @default.
• W1738803388 creator A5033558251 @default.
• W1738803388 creator A5040492776 @default.
• W1738803388 creator A5070099905 @default.
• W1738803388 creator A5072849731 @default.
• W1738803388 date "2003-01-20" @default.
• W1738803388 modified "2023-09-24" @default.
• W1738803388 title "G-Prop-II: global optimization of multilayer perceptrons using GAs" @default.
• W1738803388 cites W1505374850 @default.
• W1738803388 cites W1505725418 @default.
• W1738803388 cites W1508988787 @default.
• W1738803388 cites W1531324557 @default.
• W1738803388 cites W1533949076 @default.
• W1738803388 cites W1534784190 @default.
• W1738803388 cites W1541007220 @default.
• W1738803388 cites W1561165259 @default.
• W1738803388 cites W1562393358 @default.
• W1738803388 cites W1566243085 @default.
• W1738803388 cites W1581066146 @default.
• W1738803388 cites W1596274927 @default.
• W1738803388 cites W1602877939 @default.
• W1738803388 cites W165295313 @default.
• W1738803388 cites W1971259134 @default.
• W1738803388 cites W1971464328 @default.
• W1738803388 cites W1974770345 @default.
• W1738803388 cites W1976294505 @default.
• W1738803388 cites W2005971284 @default.
• W1738803388 cites W2009157513 @default.
• W1738803388 cites W2016490822 @default.
• W1738803388 cites W2027475699 @default.
• W1738803388 cites W2049455910 @default.
• W1738803388 cites W2050485765 @default.
• W1738803388 cites W2072245049 @default.
• W1738803388 cites W2109779438 @default.
• W1738803388 cites W2114766824 @default.
• W1738803388 cites W2126577791 @default.
• W1738803388 cites W2138033495 @default.
• W1738803388 cites W2141155619 @default.
• W1738803388 cites W2142183404 @default.
• W1738803388 cites W2143908786 @default.
• W1738803388 cites W2147368400 @default.
• W1738803388 cites W2149110629 @default.
• W1738803388 cites W2164359548 @default.
• W1738803388 cites W2166563835 @default.
• W1738803388 cites W2168874580 @default.
• W1738803388 cites W2741275920 @default.
• W1738803388 cites W3121126077 @default.
• W1738803388 cites W44465109 @default.
• W1738803388 cites W51589798 @default.
• W1738803388 cites W55255890 @default.
• W1738803388 cites W92617545 @default.
• W1738803388 doi "https://doi.org/10.1109/cec.1999.785523" @default.
• W1738803388 hasPublicationYear "2003" @default.
• W1738803388 type Work @default.
• W1738803388 sameAs 1738803388 @default.
• W1738803388 citedByCount "17" @default.
• W1738803388 countsByYear W17388033882012 @default.
• W1738803388 countsByYear W17388033882016 @default.
• W1738803388 countsByYear W17388033882020 @default.
• W1738803388 crossrefType "proceedings-article" @default.
• W1738803388 hasAuthorship W1738803388A5001935513 @default.
• W1738803388 hasAuthorship W1738803388A5023015655 @default.
• W1738803388 hasAuthorship W1738803388A5033558251 @default.
• W1738803388 hasAuthorship W1738803388A5040492776 @default.
• W1738803388 hasAuthorship W1738803388A5070099905 @default.
• W1738803388 hasAuthorship W1738803388A5072849731 @default.
• W1738803388 hasConcept C11413529 @default.
• W1738803388 hasConcept C119857082 @default.
• W1738803388 hasConcept C13280743 @default.
• W1738803388 hasConcept C134306372 @default.
• W1738803388 hasConcept C147168706 @default.
• W1738803388 hasConcept C153180895 @default.
• W1738803388 hasConcept C154945302 @default.
• W1738803388 hasConcept C155032097 @default.
• W1738803388 hasConcept C177148314 @default.
• W1738803388 hasConcept C177973122 @default.
• W1738803388 hasConcept C179717631 @default.
• W1738803388 hasConcept C185798385 @default.
• W1738803388 hasConcept C205649164 @default.
• W1738803388 hasConcept C33923547 @default.
• W1738803388 hasConcept C41008148 @default.
• W1738803388 hasConcept C50644808 @default.
• W1738803388 hasConcept C60908668 @default.
• W1738803388 hasConcept C8880873 @default.
• W1738803388 hasConcept C98359873 @default.
• W1738803388 hasConceptScore W1738803388C11413529 @default.
• W1738803388 hasConceptScore W1738803388C119857082 @default.
• W1738803388 hasConceptScore W1738803388C13280743 @default.
• W1738803388 hasConceptScore W1738803388C134306372 @default.
• W1738803388 hasConceptScore W1738803388C147168706 @default.
• W1738803388 hasConceptScore W1738803388C153180895 @default.
• W1738803388 hasConceptScore W1738803388C154945302 @default.
• W1738803388 hasConceptScore W1738803388C155032097 @default.
• W1738803388 hasConceptScore W1738803388C177148314 @default.
• W1738803388 hasConceptScore W1738803388C177973122 @default.
• W1738803388 hasConceptScore W1738803388C179717631 @default.
• W1738803388 hasConceptScore W1738803388C185798385 @default.

• next