Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136174377> ?p ?o ?g. }
- W3136174377 endingPage "3250" @default.
- W3136174377 startingPage "3237" @default.
- W3136174377 abstract "Training neural networks with the Moore–Penrose (MP) inverse has recently gained attention in view of its noniterative training nature. However, a significant drawback of learning based on the MP inverse is that the computational memory consumption grows along with the size of a dataset. In this article, based on the partitioning of the MP inverse, we propose a blockwise recursive MP inverse formulation (BRMP) for network learning with low-memory property while preserving its training effectiveness. The BRMP is an equivalent formulation to its batchwise counterpart since neither approximation nor assumption is made in the derivation process. Our further exploration of this recursive method leads to a switching structure among three different scenarios. This structure also reveals that the well-known recursive least squares method is a special case of our proposed technique. Subsequently, we apply BRMP to the training of radial basis function networks as well as multilayer perceptrons. The experimental validation covers both regression and classification tasks." @default.
- W3136174377 created "2021-03-29" @default.
- W3136174377 creator A5018473729 @default.
- W3136174377 creator A5049506273 @default.
- W3136174377 creator A5061256037 @default.
- W3136174377 date "2022-05-01" @default.
- W3136174377 modified "2023-10-16" @default.
- W3136174377 title "Blockwise Recursive Moore–Penrose Inverse for Network Learning" @default.
- W3136174377 cites W1518186130 @default.
- W3136174377 cites W1973433968 @default.
- W3136174377 cites W1988268958 @default.
- W3136174377 cites W1991166456 @default.
- W3136174377 cites W2003137566 @default.
- W3136174377 cites W2003912160 @default.
- W3136174377 cites W2016514184 @default.
- W3136174377 cites W2037727941 @default.
- W3136174377 cites W2048443683 @default.
- W3136174377 cites W2110518784 @default.
- W3136174377 cites W2113442785 @default.
- W3136174377 cites W2125485651 @default.
- W3136174377 cites W2155910151 @default.
- W3136174377 cites W2158054309 @default.
- W3136174377 cites W2167501416 @default.
- W3136174377 cites W25009767 @default.
- W3136174377 cites W2614221804 @default.
- W3136174377 cites W2615874979 @default.
- W3136174377 cites W2755486527 @default.
- W3136174377 cites W2756027689 @default.
- W3136174377 cites W2758512905 @default.
- W3136174377 cites W2894843516 @default.
- W3136174377 cites W2897502731 @default.
- W3136174377 cites W2913500645 @default.
- W3136174377 cites W2964118901 @default.
- W3136174377 cites W2970079217 @default.
- W3136174377 cites W2978138507 @default.
- W3136174377 cites W2992346182 @default.
- W3136174377 cites W3043177225 @default.
- W3136174377 cites W4237284205 @default.
- W3136174377 doi "https://doi.org/10.1109/tsmc.2021.3064241" @default.
- W3136174377 hasPublicationYear "2022" @default.
- W3136174377 type Work @default.
- W3136174377 sameAs 3136174377 @default.
- W3136174377 citedByCount "3" @default.
- W3136174377 countsByYear W31361743772023 @default.
- W3136174377 crossrefType "journal-article" @default.
- W3136174377 hasAuthorship W3136174377A5018473729 @default.
- W3136174377 hasAuthorship W3136174377A5049506273 @default.
- W3136174377 hasAuthorship W3136174377A5061256037 @default.
- W3136174377 hasConcept C111472728 @default.
- W3136174377 hasConcept C111919701 @default.
- W3136174377 hasConcept C11413529 @default.
- W3136174377 hasConcept C138885662 @default.
- W3136174377 hasConcept C140528856 @default.
- W3136174377 hasConcept C154945302 @default.
- W3136174377 hasConcept C189950617 @default.
- W3136174377 hasConcept C207467116 @default.
- W3136174377 hasConcept C2524010 @default.
- W3136174377 hasConcept C28826006 @default.
- W3136174377 hasConcept C33923547 @default.
- W3136174377 hasConcept C41008148 @default.
- W3136174377 hasConcept C50644808 @default.
- W3136174377 hasConcept C60908668 @default.
- W3136174377 hasConcept C98045186 @default.
- W3136174377 hasConcept C98856871 @default.
- W3136174377 hasConceptScore W3136174377C111472728 @default.
- W3136174377 hasConceptScore W3136174377C111919701 @default.
- W3136174377 hasConceptScore W3136174377C11413529 @default.
- W3136174377 hasConceptScore W3136174377C138885662 @default.
- W3136174377 hasConceptScore W3136174377C140528856 @default.
- W3136174377 hasConceptScore W3136174377C154945302 @default.
- W3136174377 hasConceptScore W3136174377C189950617 @default.
- W3136174377 hasConceptScore W3136174377C207467116 @default.
- W3136174377 hasConceptScore W3136174377C2524010 @default.
- W3136174377 hasConceptScore W3136174377C28826006 @default.
- W3136174377 hasConceptScore W3136174377C33923547 @default.
- W3136174377 hasConceptScore W3136174377C41008148 @default.
- W3136174377 hasConceptScore W3136174377C50644808 @default.
- W3136174377 hasConceptScore W3136174377C60908668 @default.
- W3136174377 hasConceptScore W3136174377C98045186 @default.
- W3136174377 hasConceptScore W3136174377C98856871 @default.
- W3136174377 hasFunder F4320320766 @default.
- W3136174377 hasFunder F4320322120 @default.
- W3136174377 hasIssue "5" @default.
- W3136174377 hasLocation W31361743771 @default.
- W3136174377 hasOpenAccess W3136174377 @default.
- W3136174377 hasPrimaryLocation W31361743771 @default.
- W3136174377 hasRelatedWork W1964695469 @default.
- W3136174377 hasRelatedWork W1997128020 @default.
- W3136174377 hasRelatedWork W2031485977 @default.
- W3136174377 hasRelatedWork W2298381223 @default.
- W3136174377 hasRelatedWork W2384285632 @default.
- W3136174377 hasRelatedWork W2625424124 @default.
- W3136174377 hasRelatedWork W3133467804 @default.
- W3136174377 hasRelatedWork W3136174377 @default.
- W3136174377 hasRelatedWork W4211195172 @default.
- W3136174377 hasRelatedWork W2276110787 @default.
- W3136174377 hasVolume "52" @default.
- W3136174377 isParatext "false" @default.