FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045731047> ?p ?o ?g. }

• W3045731047 endingPage "224" @default.
• W3045731047 startingPage "215" @default.
• W3045731047 abstract "Hyperparameter optimization is a challenging process that has the potential to improve machine learning algorithms. Since it creates a remarkable computational burden for machine learning tasks, there have been few works coping with tuning strategies of a specific algorithm. In this paper, an improved Stochastic Gradient Descent (SGD) based on Fisher Maximization is developed for tuning hyperparameters of an Echo State Network (ESN) which has a wide range of applications. The results of the method are then compared with those of traditional Gradient Descent and Grid Search. According to the obtained results; 1) The scale of the data sets greatly affects the reliability of hyperparameter optimization results; 2) Feature selection is critical in terms of mean error of training when hyperparameter optimization is applied on some methods such as ESN; 3) SGD falls in a good local minima if Fisher Maximization is performed to find a good starting point." @default.
• W3045731047 created "2020-08-03" @default.
• W3045731047 creator A5050461639 @default.
• W3045731047 creator A5055357850 @default.
• W3045731047 creator A5082131534 @default.
• W3045731047 date "2020-11-01" @default.
• W3045731047 modified "2023-10-18" @default.
• W3045731047 title "Optimizing echo state network through a novel fisher maximization based stochastic gradient descent" @default.
• W3045731047 cites W1036981403 @default.
• W3045731047 cites W1856316989 @default.
• W3045731047 cites W1984516841 @default.
• W3045731047 cites W1989185482 @default.
• W3045731047 cites W2001263627 @default.
• W3045731047 cites W2103628399 @default.
• W3045731047 cites W2148143831 @default.
• W3045731047 cites W2148520247 @default.
• W3045731047 cites W2264375215 @default.
• W3045731047 cites W2295142501 @default.
• W3045731047 cites W2552194003 @default.
• W3045731047 cites W2554281301 @default.
• W3045731047 cites W2585008544 @default.
• W3045731047 cites W2626923521 @default.
• W3045731047 cites W2770745161 @default.
• W3045731047 cites W2775776326 @default.
• W3045731047 cites W2793851281 @default.
• W3045731047 cites W2800467185 @default.
• W3045731047 cites W2884984074 @default.
• W3045731047 cites W2885194508 @default.
• W3045731047 cites W2899638111 @default.
• W3045731047 cites W2909771186 @default.
• W3045731047 cites W2913984695 @default.
• W3045731047 cites W2918076989 @default.
• W3045731047 cites W2921881408 @default.
• W3045731047 cites W2937590067 @default.
• W3045731047 cites W2948353014 @default.
• W3045731047 cites W2960028874 @default.
• W3045731047 cites W2963177640 @default.
• W3045731047 cites W2973663040 @default.
• W3045731047 cites W2995139801 @default.
• W3045731047 cites W2995894307 @default.
• W3045731047 cites W3010938659 @default.
• W3045731047 cites W4246900739 @default.
• W3045731047 doi "https://doi.org/10.1016/j.neucom.2020.07.034" @default.
• W3045731047 hasPublicationYear "2020" @default.
• W3045731047 type Work @default.
• W3045731047 sameAs 3045731047 @default.
• W3045731047 citedByCount "11" @default.
• W3045731047 countsByYear W30457310472020 @default.
• W3045731047 countsByYear W30457310472021 @default.
• W3045731047 countsByYear W30457310472022 @default.
• W3045731047 countsByYear W30457310472023 @default.
• W3045731047 crossrefType "journal-article" @default.
• W3045731047 hasAuthorship W3045731047A5050461639 @default.
• W3045731047 hasAuthorship W3045731047A5055357850 @default.
• W3045731047 hasAuthorship W3045731047A5082131534 @default.
• W3045731047 hasConcept C10485038 @default.
• W3045731047 hasConcept C11413529 @default.
• W3045731047 hasConcept C119857082 @default.
• W3045731047 hasConcept C12267149 @default.
• W3045731047 hasConcept C126255220 @default.
• W3045731047 hasConcept C134306372 @default.
• W3045731047 hasConcept C153258448 @default.
• W3045731047 hasConcept C154945302 @default.
• W3045731047 hasConcept C186633575 @default.
• W3045731047 hasConcept C206688291 @default.
• W3045731047 hasConcept C2776330181 @default.
• W3045731047 hasConcept C33923547 @default.
• W3045731047 hasConcept C41008148 @default.
• W3045731047 hasConcept C50644808 @default.
• W3045731047 hasConcept C8642999 @default.
• W3045731047 hasConceptScore W3045731047C10485038 @default.
• W3045731047 hasConceptScore W3045731047C11413529 @default.
• W3045731047 hasConceptScore W3045731047C119857082 @default.
• W3045731047 hasConceptScore W3045731047C12267149 @default.
• W3045731047 hasConceptScore W3045731047C126255220 @default.
• W3045731047 hasConceptScore W3045731047C134306372 @default.
• W3045731047 hasConceptScore W3045731047C153258448 @default.
• W3045731047 hasConceptScore W3045731047C154945302 @default.
• W3045731047 hasConceptScore W3045731047C186633575 @default.
• W3045731047 hasConceptScore W3045731047C206688291 @default.
• W3045731047 hasConceptScore W3045731047C2776330181 @default.
• W3045731047 hasConceptScore W3045731047C33923547 @default.
• W3045731047 hasConceptScore W3045731047C41008148 @default.
• W3045731047 hasConceptScore W3045731047C50644808 @default.
• W3045731047 hasConceptScore W3045731047C8642999 @default.
• W3045731047 hasLocation W30457310471 @default.
• W3045731047 hasOpenAccess W3045731047 @default.
• W3045731047 hasPrimaryLocation W30457310471 @default.
• W3045731047 hasRelatedWork W2266822037 @default.
• W3045731047 hasRelatedWork W3152685838 @default.
• W3045731047 hasRelatedWork W3192751261 @default.
• W3045731047 hasRelatedWork W4280535922 @default.
• W3045731047 hasRelatedWork W4283697347 @default.
• W3045731047 hasRelatedWork W4287027148 @default.
• W3045731047 hasRelatedWork W4295309597 @default.
• W3045731047 hasRelatedWork W4298144215 @default.
• W3045731047 hasRelatedWork W4313854490 @default.
• W3045731047 hasRelatedWork W4323894855 @default.

• next