Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890930691> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W2890930691 abstract "In the present work, we investigate the possibility to expand existing Deep Learning solvers in order to improve the quality and stability of the training. We propose different new solvers, all of them based on the filtering of the neural network parameters, and experimentally prove that properly tuning their respective hyper-parameters leads to a clear improvement of the training and validation results, in quality and in stability." @default.
- W2890930691 created "2018-09-27" @default.
- W2890930691 creator A5044999283 @default.
- W2890930691 creator A5046390881 @default.
- W2890930691 creator A5067792459 @default.
- W2890930691 creator A5084035589 @default.
- W2890930691 date "2018-10-01" @default.
- W2890930691 modified "2023-09-26" @default.
- W2890930691 title "Increasing Training Stability for Deep CNNS" @default.
- W2890930691 cites W1608292140 @default.
- W2890930691 cites W2086161653 @default.
- W2890930691 cites W2146502635 @default.
- W2890930691 cites W2146989110 @default.
- W2890930691 cites W2964121744 @default.
- W2890930691 doi "https://doi.org/10.1109/icip.2018.8451570" @default.
- W2890930691 hasPublicationYear "2018" @default.
- W2890930691 type Work @default.
- W2890930691 sameAs 2890930691 @default.
- W2890930691 citedByCount "1" @default.
- W2890930691 countsByYear W28909306912012 @default.
- W2890930691 crossrefType "proceedings-article" @default.
- W2890930691 hasAuthorship W2890930691A5044999283 @default.
- W2890930691 hasAuthorship W2890930691A5046390881 @default.
- W2890930691 hasAuthorship W2890930691A5067792459 @default.
- W2890930691 hasAuthorship W2890930691A5084035589 @default.
- W2890930691 hasConcept C112972136 @default.
- W2890930691 hasConcept C119857082 @default.
- W2890930691 hasConcept C153180895 @default.
- W2890930691 hasConcept C153294291 @default.
- W2890930691 hasConcept C154945302 @default.
- W2890930691 hasConcept C205649164 @default.
- W2890930691 hasConcept C2777211547 @default.
- W2890930691 hasConcept C41008148 @default.
- W2890930691 hasConceptScore W2890930691C112972136 @default.
- W2890930691 hasConceptScore W2890930691C119857082 @default.
- W2890930691 hasConceptScore W2890930691C153180895 @default.
- W2890930691 hasConceptScore W2890930691C153294291 @default.
- W2890930691 hasConceptScore W2890930691C154945302 @default.
- W2890930691 hasConceptScore W2890930691C205649164 @default.
- W2890930691 hasConceptScore W2890930691C2777211547 @default.
- W2890930691 hasConceptScore W2890930691C41008148 @default.
- W2890930691 hasLocation W28909306911 @default.
- W2890930691 hasLocation W28909306912 @default.
- W2890930691 hasLocation W28909306913 @default.
- W2890930691 hasOpenAccess W2890930691 @default.
- W2890930691 hasPrimaryLocation W28909306911 @default.
- W2890930691 hasRelatedWork W2033914206 @default.
- W2890930691 hasRelatedWork W2042327336 @default.
- W2890930691 hasRelatedWork W2046077695 @default.
- W2890930691 hasRelatedWork W2146076056 @default.
- W2890930691 hasRelatedWork W2163831990 @default.
- W2890930691 hasRelatedWork W2378160586 @default.
- W2890930691 hasRelatedWork W2996038082 @default.
- W2890930691 hasRelatedWork W3003836766 @default.
- W2890930691 hasRelatedWork W3047965787 @default.
- W2890930691 hasRelatedWork W3184582087 @default.
- W2890930691 isParatext "false" @default.
- W2890930691 isRetracted "false" @default.
- W2890930691 magId "2890930691" @default.
- W2890930691 workType "article" @default.