Matches in SemOpenAlex for { <https://semopenalex.org/work/W2294698971> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2294698971 endingPage "210" @default.
- W2294698971 startingPage "180" @default.
- W2294698971 abstract "Superlinear algorithms are highly regarded for the speed-complexity ratio. With superlinear convergence rates and linear computational complexity they are the primary choice for large scale tasks. However, varying performance on different tasks rises the question of relationship between an algorithm and a task it is applied to. To approach the issue we establish a classification framework for both algorithms and tasks. The proposed classification framework permits independent specification of functions and optimization techniques. Within this framework the task of training MLP neural networks is classified. The presented theoretical material allows design of superlinear first order algorithms tailored to particular task. We introduce two such techniques with a line search subproblem simplified to a single step calculation of the appropriate values of step length and/or momentum term. It remarkably simplifies the implementation and computational complexity of the line search subproblem and yet does not harm the stability of the methods. The algorithms are theoretically proved convergent. Performance of the algorithms is extensively evaluated on five data sets and compared to the relevant first order optimization techniques.Key wordsfirst order optimizationsuperlinear convergence raterssteepest descentconjugate gradientline searchclassification frameworkneural networks" @default.
- W2294698971 created "2016-06-24" @default.
- W2294698971 creator A5011066581 @default.
- W2294698971 creator A5074072243 @default.
- W2294698971 date "2004-01-01" @default.
- W2294698971 modified "2023-09-27" @default.
- W2294698971 title "Superlinear Learning Algorithm Design" @default.
- W2294698971 cites W1491720843 @default.
- W2294698971 cites W1967628877 @default.
- W2294698971 cites W1977770529 @default.
- W2294698971 cites W1978515644 @default.
- W2294698971 cites W1981220283 @default.
- W2294698971 cites W1988849934 @default.
- W2294698971 cites W2010581677 @default.
- W2294698971 cites W2022772618 @default.
- W2294698971 cites W2033245860 @default.
- W2294698971 cites W2050786966 @default.
- W2294698971 cites W2054833248 @default.
- W2294698971 cites W2083918846 @default.
- W2294698971 cites W2113287505 @default.
- W2294698971 cites W2122565324 @default.
- W2294698971 cites W2123224804 @default.
- W2294698971 cites W2137983211 @default.
- W2294698971 cites W2160208155 @default.
- W2294698971 doi "https://doi.org/10.1007/978-3-540-39935-3_11" @default.
- W2294698971 hasPublicationYear "2004" @default.
- W2294698971 type Work @default.
- W2294698971 sameAs 2294698971 @default.
- W2294698971 citedByCount "0" @default.
- W2294698971 crossrefType "book-chapter" @default.
- W2294698971 hasAuthorship W2294698971A5011066581 @default.
- W2294698971 hasAuthorship W2294698971A5074072243 @default.
- W2294698971 hasConcept C112972136 @default.
- W2294698971 hasConcept C11413529 @default.
- W2294698971 hasConcept C119857082 @default.
- W2294698971 hasConcept C121332964 @default.
- W2294698971 hasConcept C126255220 @default.
- W2294698971 hasConcept C154945302 @default.
- W2294698971 hasConcept C162324750 @default.
- W2294698971 hasConcept C178635117 @default.
- W2294698971 hasConcept C179799912 @default.
- W2294698971 hasConcept C187736073 @default.
- W2294698971 hasConcept C2777303404 @default.
- W2294698971 hasConcept C2780451532 @default.
- W2294698971 hasConcept C33923547 @default.
- W2294698971 hasConcept C38652104 @default.
- W2294698971 hasConcept C41008148 @default.
- W2294698971 hasConcept C50522688 @default.
- W2294698971 hasConcept C50644808 @default.
- W2294698971 hasConcept C61797465 @default.
- W2294698971 hasConcept C62520636 @default.
- W2294698971 hasConcept C85522705 @default.
- W2294698971 hasConceptScore W2294698971C112972136 @default.
- W2294698971 hasConceptScore W2294698971C11413529 @default.
- W2294698971 hasConceptScore W2294698971C119857082 @default.
- W2294698971 hasConceptScore W2294698971C121332964 @default.
- W2294698971 hasConceptScore W2294698971C126255220 @default.
- W2294698971 hasConceptScore W2294698971C154945302 @default.
- W2294698971 hasConceptScore W2294698971C162324750 @default.
- W2294698971 hasConceptScore W2294698971C178635117 @default.
- W2294698971 hasConceptScore W2294698971C179799912 @default.
- W2294698971 hasConceptScore W2294698971C187736073 @default.
- W2294698971 hasConceptScore W2294698971C2777303404 @default.
- W2294698971 hasConceptScore W2294698971C2780451532 @default.
- W2294698971 hasConceptScore W2294698971C33923547 @default.
- W2294698971 hasConceptScore W2294698971C38652104 @default.
- W2294698971 hasConceptScore W2294698971C41008148 @default.
- W2294698971 hasConceptScore W2294698971C50522688 @default.
- W2294698971 hasConceptScore W2294698971C50644808 @default.
- W2294698971 hasConceptScore W2294698971C61797465 @default.
- W2294698971 hasConceptScore W2294698971C62520636 @default.
- W2294698971 hasConceptScore W2294698971C85522705 @default.
- W2294698971 hasLocation W22946989711 @default.
- W2294698971 hasOpenAccess W2294698971 @default.
- W2294698971 hasPrimaryLocation W22946989711 @default.
- W2294698971 hasRelatedWork W1593440482 @default.
- W2294698971 hasRelatedWork W2015080260 @default.
- W2294698971 hasRelatedWork W2072260865 @default.
- W2294698971 hasRelatedWork W2079309016 @default.
- W2294698971 hasRelatedWork W2106461442 @default.
- W2294698971 hasRelatedWork W2128886773 @default.
- W2294698971 hasRelatedWork W2356755074 @default.
- W2294698971 hasRelatedWork W2381210555 @default.
- W2294698971 hasRelatedWork W657818131 @default.
- W2294698971 hasRelatedWork W2124799266 @default.
- W2294698971 isParatext "false" @default.
- W2294698971 isRetracted "false" @default.
- W2294698971 magId "2294698971" @default.
- W2294698971 workType "book-chapter" @default.