Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226105952> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4226105952 abstract "Training convolutional neural networks (CNNs) with back-propagation (BP) is time-consuming and resource-intensive particularly in view of the need to visit the dataset multiple times. In contrast, analytic learning attempts to obtain the weights in one epoch. However, existing attempts to analytic learning considered only the multilayer perceptron (MLP). In this article, we propose an analytic convolutional neural network learning (ACnnL). Theoretically we show that ACnnL builds a closed-form solution similar to its MLP counterpart, but differs in their regularization constraints. Consequently, we are able to answer to a certain extent why CNNs usually generalize better than MLPs from the implicit regularization point of view. The ACnnL is validated by conducting classification tasks on several benchmark datasets. It is encouraging that the ACnnL trains CNNs in a significantly fast manner with reasonably close prediction accuracies to those using BP. Moreover, our experiments disclose a unique advantage of ACnnL under the small-sample scenario when training data are scarce or expensive." @default.
- W4226105952 created "2022-05-05" @default.
- W4226105952 creator A5018473729 @default.
- W4226105952 creator A5049506273 @default.
- W4226105952 creator A5056357562 @default.
- W4226105952 creator A5061256037 @default.
- W4226105952 date "2022-02-14" @default.
- W4226105952 modified "2023-10-16" @default.
- W4226105952 title "Analytic Learning of Convolutional Neural Network For Pattern Recognition" @default.
- W4226105952 doi "https://doi.org/10.48550/arxiv.2202.06504" @default.
- W4226105952 hasPublicationYear "2022" @default.
- W4226105952 type Work @default.
- W4226105952 citedByCount "0" @default.
- W4226105952 crossrefType "posted-content" @default.
- W4226105952 hasAuthorship W4226105952A5018473729 @default.
- W4226105952 hasAuthorship W4226105952A5049506273 @default.
- W4226105952 hasAuthorship W4226105952A5056357562 @default.
- W4226105952 hasAuthorship W4226105952A5061256037 @default.
- W4226105952 hasBestOaLocation W42261059521 @default.
- W4226105952 hasConcept C108583219 @default.
- W4226105952 hasConcept C119857082 @default.
- W4226105952 hasConcept C13280743 @default.
- W4226105952 hasConcept C153180895 @default.
- W4226105952 hasConcept C154945302 @default.
- W4226105952 hasConcept C155032097 @default.
- W4226105952 hasConcept C179717631 @default.
- W4226105952 hasConcept C185798385 @default.
- W4226105952 hasConcept C205649164 @default.
- W4226105952 hasConcept C2776135515 @default.
- W4226105952 hasConcept C41008148 @default.
- W4226105952 hasConcept C50644808 @default.
- W4226105952 hasConcept C81363708 @default.
- W4226105952 hasConceptScore W4226105952C108583219 @default.
- W4226105952 hasConceptScore W4226105952C119857082 @default.
- W4226105952 hasConceptScore W4226105952C13280743 @default.
- W4226105952 hasConceptScore W4226105952C153180895 @default.
- W4226105952 hasConceptScore W4226105952C154945302 @default.
- W4226105952 hasConceptScore W4226105952C155032097 @default.
- W4226105952 hasConceptScore W4226105952C179717631 @default.
- W4226105952 hasConceptScore W4226105952C185798385 @default.
- W4226105952 hasConceptScore W4226105952C205649164 @default.
- W4226105952 hasConceptScore W4226105952C2776135515 @default.
- W4226105952 hasConceptScore W4226105952C41008148 @default.
- W4226105952 hasConceptScore W4226105952C50644808 @default.
- W4226105952 hasConceptScore W4226105952C81363708 @default.
- W4226105952 hasLocation W42261059521 @default.
- W4226105952 hasOpenAccess W4226105952 @default.
- W4226105952 hasPrimaryLocation W42261059521 @default.
- W4226105952 hasRelatedWork W2337926734 @default.
- W4226105952 hasRelatedWork W2732542196 @default.
- W4226105952 hasRelatedWork W2738221750 @default.
- W4226105952 hasRelatedWork W2763109982 @default.
- W4226105952 hasRelatedWork W2963958939 @default.
- W4226105952 hasRelatedWork W4311257506 @default.
- W4226105952 hasRelatedWork W4319994054 @default.
- W4226105952 hasRelatedWork W4320802194 @default.
- W4226105952 hasRelatedWork W4327499916 @default.
- W4226105952 hasRelatedWork W564581980 @default.
- W4226105952 isParatext "false" @default.
- W4226105952 isRetracted "false" @default.
- W4226105952 workType "article" @default.