Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894582337> ?p ?o ?g. }
- W2894582337 endingPage "526" @default.
- W2894582337 startingPage "509" @default.
- W2894582337 abstract "Deep-Learning has become a leading strategy for artificial intelligence and is being applied in many fields due to its excellent performance that has surpassed human cognitive abilities in a number of classification and control problems (Ciregan, Meier, & Schmidhuber, 2012; Mnih et al., 2015). However, the training process of Deep-Learning is usually slow and requires high-performance computing, capable of handling large datasets. The optimization of the training method can improve the learning rate of the Deep-Learning networks and result in a higher performance while using the same number of training epochs (cycles). This paper considers the use of estimation theory for training of large neural networks and in particular Deep-Learning networks. Two estimation strategies namely the Extended Kalman Filter (EKF) and the Smooth Variable Structure Filter (SVSF) have been revised (subsequently referred to as RSVSF and REKF) and used for network training. They are applied to several benchmark datasets and comparatively evaluated." @default.
- W2894582337 created "2018-10-12" @default.
- W2894582337 creator A5064053734 @default.
- W2894582337 creator A5064349407 @default.
- W2894582337 creator A5081811342 @default.
- W2894582337 creator A5088190674 @default.
- W2894582337 date "2018-12-01" @default.
- W2894582337 modified "2023-09-28" @default.
- W2894582337 title "Estimation theory and Neural Networks revisited: REKF and RSVSF as optimization techniques for Deep-Learning" @default.
- W2894582337 cites W1583951317 @default.
- W2894582337 cites W1970789124 @default.
- W2894582337 cites W1980287119 @default.
- W2894582337 cites W1990470142 @default.
- W2894582337 cites W2006544565 @default.
- W2894582337 cites W2007339694 @default.
- W2894582337 cites W2012231377 @default.
- W2894582337 cites W2014863553 @default.
- W2894582337 cites W2043382734 @default.
- W2894582337 cites W2046084401 @default.
- W2894582337 cites W2051812123 @default.
- W2894582337 cites W2060562008 @default.
- W2894582337 cites W2061781302 @default.
- W2894582337 cites W2067497490 @default.
- W2894582337 cites W2072643303 @default.
- W2894582337 cites W2076063813 @default.
- W2894582337 cites W2083402998 @default.
- W2894582337 cites W2087070363 @default.
- W2894582337 cites W2091549324 @default.
- W2894582337 cites W2095907915 @default.
- W2894582337 cites W2105934661 @default.
- W2894582337 cites W2132152975 @default.
- W2894582337 cites W2132424367 @default.
- W2894582337 cites W2140060924 @default.
- W2894582337 cites W2141125852 @default.
- W2894582337 cites W2144349051 @default.
- W2894582337 cites W2145339207 @default.
- W2894582337 cites W2148551624 @default.
- W2894582337 cites W2150913357 @default.
- W2894582337 cites W2155482699 @default.
- W2894582337 cites W2159065647 @default.
- W2894582337 cites W2167002981 @default.
- W2894582337 cites W2169791674 @default.
- W2894582337 cites W2171869556 @default.
- W2894582337 cites W2264980173 @default.
- W2894582337 cites W2309796998 @default.
- W2894582337 cites W2766736793 @default.
- W2894582337 cites W4231109964 @default.
- W2894582337 doi "https://doi.org/10.1016/j.neunet.2018.09.012" @default.
- W2894582337 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30336326" @default.
- W2894582337 hasPublicationYear "2018" @default.
- W2894582337 type Work @default.
- W2894582337 sameAs 2894582337 @default.
- W2894582337 citedByCount "8" @default.
- W2894582337 countsByYear W28945823372019 @default.
- W2894582337 countsByYear W28945823372020 @default.
- W2894582337 countsByYear W28945823372021 @default.
- W2894582337 countsByYear W28945823372022 @default.
- W2894582337 countsByYear W28945823372023 @default.
- W2894582337 crossrefType "journal-article" @default.
- W2894582337 hasAuthorship W2894582337A5064053734 @default.
- W2894582337 hasAuthorship W2894582337A5064349407 @default.
- W2894582337 hasAuthorship W2894582337A5081811342 @default.
- W2894582337 hasAuthorship W2894582337A5088190674 @default.
- W2894582337 hasConcept C108583219 @default.
- W2894582337 hasConcept C111919701 @default.
- W2894582337 hasConcept C119857082 @default.
- W2894582337 hasConcept C13280743 @default.
- W2894582337 hasConcept C154945302 @default.
- W2894582337 hasConcept C157286648 @default.
- W2894582337 hasConcept C185798385 @default.
- W2894582337 hasConcept C205649164 @default.
- W2894582337 hasConcept C206833254 @default.
- W2894582337 hasConcept C41008148 @default.
- W2894582337 hasConcept C50644808 @default.
- W2894582337 hasConcept C98045186 @default.
- W2894582337 hasConceptScore W2894582337C108583219 @default.
- W2894582337 hasConceptScore W2894582337C111919701 @default.
- W2894582337 hasConceptScore W2894582337C119857082 @default.
- W2894582337 hasConceptScore W2894582337C13280743 @default.
- W2894582337 hasConceptScore W2894582337C154945302 @default.
- W2894582337 hasConceptScore W2894582337C157286648 @default.
- W2894582337 hasConceptScore W2894582337C185798385 @default.
- W2894582337 hasConceptScore W2894582337C205649164 @default.
- W2894582337 hasConceptScore W2894582337C206833254 @default.
- W2894582337 hasConceptScore W2894582337C41008148 @default.
- W2894582337 hasConceptScore W2894582337C50644808 @default.
- W2894582337 hasConceptScore W2894582337C98045186 @default.
- W2894582337 hasFunder F4320334593 @default.
- W2894582337 hasLocation W28945823371 @default.
- W2894582337 hasLocation W28945823372 @default.
- W2894582337 hasOpenAccess W2894582337 @default.
- W2894582337 hasPrimaryLocation W28945823371 @default.
- W2894582337 hasRelatedWork W3014300295 @default.
- W2894582337 hasRelatedWork W3164822677 @default.
- W2894582337 hasRelatedWork W4223943233 @default.
- W2894582337 hasRelatedWork W4225161397 @default.
- W2894582337 hasRelatedWork W4250304930 @default.
- W2894582337 hasRelatedWork W4312200629 @default.