Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901390526> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2901390526 abstract "A recent research interest on deep neural networks is to understand why deep networks are preferred to shallow networks. In this article, we considered an advantage of a deep structure in realizing a heaviside function in training. This is significant not only as simple classification problems but also as a basis in constructing general non-smooth functions. A heaviside function can be well approximated by a difference of ReLUs if we can set extremely large weight values. However, it is not so easy to attain them in training. We showed that a heaviside function can be well represented without large weight values if we employ a deep structure. We also showed that update terms of weights at input side can be necessarily large if a network is trained to realize a heaviside function. Therefore, apparent acceleration of training is brought about by setting a small learning rate. As a result, we can say that, by employing a deep structure, a good fitting of heaviside function can be obtained within a reasonable training time under a moderate small learning rate. Our results suggest that a deep structure is effective in a practical training that requires a discontinuous output." @default.
- W2901390526 created "2018-11-29" @default.
- W2901390526 creator A5089468899 @default.
- W2901390526 date "2018-01-01" @default.
- W2901390526 modified "2023-09-27" @default.
- W2901390526 title "On a Fitting of a Heaviside Function by Deep ReLU Neural Networks" @default.
- W2901390526 cites W2074472353 @default.
- W2901390526 cites W2076063813 @default.
- W2901390526 cites W2107878631 @default.
- W2901390526 cites W2528305538 @default.
- W2901390526 cites W2963146412 @default.
- W2901390526 doi "https://doi.org/10.1007/978-3-030-04167-0_6" @default.
- W2901390526 hasPublicationYear "2018" @default.
- W2901390526 type Work @default.
- W2901390526 sameAs 2901390526 @default.
- W2901390526 citedByCount "0" @default.
- W2901390526 crossrefType "book-chapter" @default.
- W2901390526 hasAuthorship W2901390526A5089468899 @default.
- W2901390526 hasConcept C108583219 @default.
- W2901390526 hasConcept C11413529 @default.
- W2901390526 hasConcept C117896860 @default.
- W2901390526 hasConcept C121332964 @default.
- W2901390526 hasConcept C134306372 @default.
- W2901390526 hasConcept C14036430 @default.
- W2901390526 hasConcept C154945302 @default.
- W2901390526 hasConcept C33923547 @default.
- W2901390526 hasConcept C38365724 @default.
- W2901390526 hasConcept C41008148 @default.
- W2901390526 hasConcept C50644808 @default.
- W2901390526 hasConcept C74650414 @default.
- W2901390526 hasConcept C78458016 @default.
- W2901390526 hasConcept C7980502 @default.
- W2901390526 hasConcept C86803240 @default.
- W2901390526 hasConceptScore W2901390526C108583219 @default.
- W2901390526 hasConceptScore W2901390526C11413529 @default.
- W2901390526 hasConceptScore W2901390526C117896860 @default.
- W2901390526 hasConceptScore W2901390526C121332964 @default.
- W2901390526 hasConceptScore W2901390526C134306372 @default.
- W2901390526 hasConceptScore W2901390526C14036430 @default.
- W2901390526 hasConceptScore W2901390526C154945302 @default.
- W2901390526 hasConceptScore W2901390526C33923547 @default.
- W2901390526 hasConceptScore W2901390526C38365724 @default.
- W2901390526 hasConceptScore W2901390526C41008148 @default.
- W2901390526 hasConceptScore W2901390526C50644808 @default.
- W2901390526 hasConceptScore W2901390526C74650414 @default.
- W2901390526 hasConceptScore W2901390526C78458016 @default.
- W2901390526 hasConceptScore W2901390526C7980502 @default.
- W2901390526 hasConceptScore W2901390526C86803240 @default.
- W2901390526 hasLocation W29013905261 @default.
- W2901390526 hasOpenAccess W2901390526 @default.
- W2901390526 hasPrimaryLocation W29013905261 @default.
- W2901390526 hasRelatedWork W1628717471 @default.
- W2901390526 hasRelatedWork W1946375465 @default.
- W2901390526 hasRelatedWork W2113517874 @default.
- W2901390526 hasRelatedWork W2179686778 @default.
- W2901390526 hasRelatedWork W2797092076 @default.
- W2901390526 hasRelatedWork W2881426224 @default.
- W2901390526 hasRelatedWork W2906264008 @default.
- W2901390526 hasRelatedWork W2962847207 @default.
- W2901390526 hasRelatedWork W2964520230 @default.
- W2901390526 hasRelatedWork W2970183818 @default.
- W2901390526 hasRelatedWork W2979823801 @default.
- W2901390526 hasRelatedWork W2993367001 @default.
- W2901390526 hasRelatedWork W2997208817 @default.
- W2901390526 hasRelatedWork W3021189130 @default.
- W2901390526 hasRelatedWork W3033103365 @default.
- W2901390526 hasRelatedWork W3035635935 @default.
- W2901390526 hasRelatedWork W3173582753 @default.
- W2901390526 hasRelatedWork W3187631199 @default.
- W2901390526 hasRelatedWork W3207608531 @default.
- W2901390526 hasRelatedWork W3214023269 @default.
- W2901390526 isParatext "false" @default.
- W2901390526 isRetracted "false" @default.
- W2901390526 magId "2901390526" @default.
- W2901390526 workType "book-chapter" @default.