Matches in SemOpenAlex for { <https://semopenalex.org/work/W2489672073> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2489672073 abstract "This paper describes a new approach to feed-forward neural networks learning based on a random choice of a set of neurons which are temporally active in the process of neural network weight adaptation. The rest of the network weights is locked out (frozen). In contrast to the “dropout” method introduced by Hinton et al. [15], the neurons (along with their connections) are not removed from the neural network during training, only their weights are not modified, i.e. stay constant. This means that in every epoch of training only the random part of the neural networks (a chosen set of neurons and its connections) adapts. Freezing of neurons suppresses overfitting and prevents drastic increment of weights during the learning process, since the overall structure of the neural networks does not change. In many cases the approach based on training only some parts of the neural network (subspaces of the weight space) shortens the time of training. Experimental results for medium size neural networks used for modeling regression are also provided." @default.
- W2489672073 created "2016-08-23" @default.
- W2489672073 creator A5064805184 @default.
- W2489672073 date "2016-01-01" @default.
- W2489672073 modified "2023-09-23" @default.
- W2489672073 title "Training Neural Networks by Optimizing Random Subspaces of the Weight Space" @default.
- W2489672073 cites W1988115241 @default.
- W2489672073 cites W2007272376 @default.
- W2489672073 cites W2062227835 @default.
- W2489672073 cites W2076063813 @default.
- W2489672073 cites W2078626246 @default.
- W2489672073 cites W2099579348 @default.
- W2489672073 cites W2103496339 @default.
- W2489672073 cites W2111072639 @default.
- W2489672073 cites W2136922672 @default.
- W2489672073 cites W2919115771 @default.
- W2489672073 cites W4231109964 @default.
- W2489672073 cites W4292363360 @default.
- W2489672073 doi "https://doi.org/10.1007/978-3-319-39378-0_14" @default.
- W2489672073 hasPublicationYear "2016" @default.
- W2489672073 type Work @default.
- W2489672073 sameAs 2489672073 @default.
- W2489672073 citedByCount "1" @default.
- W2489672073 countsByYear W24896720732020 @default.
- W2489672073 crossrefType "book-chapter" @default.
- W2489672073 hasAuthorship W2489672073A5064805184 @default.
- W2489672073 hasConcept C111919701 @default.
- W2489672073 hasConcept C11413529 @default.
- W2489672073 hasConcept C119857082 @default.
- W2489672073 hasConcept C12362212 @default.
- W2489672073 hasConcept C154945302 @default.
- W2489672073 hasConcept C175202392 @default.
- W2489672073 hasConcept C177264268 @default.
- W2489672073 hasConcept C199360897 @default.
- W2489672073 hasConcept C22019652 @default.
- W2489672073 hasConcept C2524010 @default.
- W2489672073 hasConcept C2776145597 @default.
- W2489672073 hasConcept C33923547 @default.
- W2489672073 hasConcept C41008148 @default.
- W2489672073 hasConcept C47702885 @default.
- W2489672073 hasConcept C50644808 @default.
- W2489672073 hasConcept C98045186 @default.
- W2489672073 hasConceptScore W2489672073C111919701 @default.
- W2489672073 hasConceptScore W2489672073C11413529 @default.
- W2489672073 hasConceptScore W2489672073C119857082 @default.
- W2489672073 hasConceptScore W2489672073C12362212 @default.
- W2489672073 hasConceptScore W2489672073C154945302 @default.
- W2489672073 hasConceptScore W2489672073C175202392 @default.
- W2489672073 hasConceptScore W2489672073C177264268 @default.
- W2489672073 hasConceptScore W2489672073C199360897 @default.
- W2489672073 hasConceptScore W2489672073C22019652 @default.
- W2489672073 hasConceptScore W2489672073C2524010 @default.
- W2489672073 hasConceptScore W2489672073C2776145597 @default.
- W2489672073 hasConceptScore W2489672073C33923547 @default.
- W2489672073 hasConceptScore W2489672073C41008148 @default.
- W2489672073 hasConceptScore W2489672073C47702885 @default.
- W2489672073 hasConceptScore W2489672073C50644808 @default.
- W2489672073 hasConceptScore W2489672073C98045186 @default.
- W2489672073 hasLocation W24896720731 @default.
- W2489672073 hasOpenAccess W2489672073 @default.
- W2489672073 hasPrimaryLocation W24896720731 @default.
- W2489672073 hasRelatedWork W124100583 @default.
- W2489672073 hasRelatedWork W1958277471 @default.
- W2489672073 hasRelatedWork W1968756388 @default.
- W2489672073 hasRelatedWork W2005971284 @default.
- W2489672073 hasRelatedWork W2156892070 @default.
- W2489672073 hasRelatedWork W2167924420 @default.
- W2489672073 hasRelatedWork W2181382924 @default.
- W2489672073 hasRelatedWork W2363648501 @default.
- W2489672073 hasRelatedWork W2389539679 @default.
- W2489672073 hasRelatedWork W2617241165 @default.
- W2489672073 hasRelatedWork W2892355103 @default.
- W2489672073 hasRelatedWork W3197904945 @default.
- W2489672073 hasRelatedWork W3781714 @default.
- W2489672073 hasRelatedWork W1003055588 @default.
- W2489672073 hasRelatedWork W2188111966 @default.
- W2489672073 hasRelatedWork W2851267768 @default.
- W2489672073 hasRelatedWork W2948055396 @default.
- W2489672073 hasRelatedWork W3039814340 @default.
- W2489672073 hasRelatedWork W3063450679 @default.
- W2489672073 hasRelatedWork W3179492898 @default.
- W2489672073 isParatext "false" @default.
- W2489672073 isRetracted "false" @default.
- W2489672073 magId "2489672073" @default.
- W2489672073 workType "book-chapter" @default.