Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283383761> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4283383761 abstract "We state concentration inequalities for the output of the hidden layers of a stochastic deep neural network (SDNN), as well as for the output of the whole SDNN. These results allow us to introduce an expected classifier (EC), and to give probabilistic upper bound for the classification error of the EC. We also state the optimal number of layers for the SDNN via an optimal stopping procedure. We apply our analysis to a stochastic version of a feedforward neural network with ReLU activation function." @default.
- W4283383761 created "2022-06-25" @default.
- W4283383761 creator A5000098655 @default.
- W4283383761 creator A5036208626 @default.
- W4283383761 date "2022-06-22" @default.
- W4283383761 modified "2023-09-26" @default.
- W4283383761 title "Concentration inequalities and optimal number of layers for stochastic deep neural networks" @default.
- W4283383761 doi "https://doi.org/10.48550/arxiv.2206.11241" @default.
- W4283383761 hasPublicationYear "2022" @default.
- W4283383761 type Work @default.
- W4283383761 citedByCount "0" @default.
- W4283383761 crossrefType "posted-content" @default.
- W4283383761 hasAuthorship W4283383761A5000098655 @default.
- W4283383761 hasAuthorship W4283383761A5036208626 @default.
- W4283383761 hasBestOaLocation W42833837611 @default.
- W4283383761 hasConcept C11413529 @default.
- W4283383761 hasConcept C134306372 @default.
- W4283383761 hasConcept C134342201 @default.
- W4283383761 hasConcept C147168706 @default.
- W4283383761 hasConcept C154945302 @default.
- W4283383761 hasConcept C175202392 @default.
- W4283383761 hasConcept C33923547 @default.
- W4283383761 hasConcept C38365724 @default.
- W4283383761 hasConcept C41008148 @default.
- W4283383761 hasConcept C47702885 @default.
- W4283383761 hasConcept C48103436 @default.
- W4283383761 hasConcept C49937458 @default.
- W4283383761 hasConcept C50644808 @default.
- W4283383761 hasConcept C77553402 @default.
- W4283383761 hasConcept C86582703 @default.
- W4283383761 hasConcept C95623464 @default.
- W4283383761 hasConceptScore W4283383761C11413529 @default.
- W4283383761 hasConceptScore W4283383761C134306372 @default.
- W4283383761 hasConceptScore W4283383761C134342201 @default.
- W4283383761 hasConceptScore W4283383761C147168706 @default.
- W4283383761 hasConceptScore W4283383761C154945302 @default.
- W4283383761 hasConceptScore W4283383761C175202392 @default.
- W4283383761 hasConceptScore W4283383761C33923547 @default.
- W4283383761 hasConceptScore W4283383761C38365724 @default.
- W4283383761 hasConceptScore W4283383761C41008148 @default.
- W4283383761 hasConceptScore W4283383761C47702885 @default.
- W4283383761 hasConceptScore W4283383761C48103436 @default.
- W4283383761 hasConceptScore W4283383761C49937458 @default.
- W4283383761 hasConceptScore W4283383761C50644808 @default.
- W4283383761 hasConceptScore W4283383761C77553402 @default.
- W4283383761 hasConceptScore W4283383761C86582703 @default.
- W4283383761 hasConceptScore W4283383761C95623464 @default.
- W4283383761 hasLocation W42833837611 @default.
- W4283383761 hasOpenAccess W4283383761 @default.
- W4283383761 hasPrimaryLocation W42833837611 @default.
- W4283383761 hasRelatedWork W1595652908 @default.
- W4283383761 hasRelatedWork W2014323024 @default.
- W4283383761 hasRelatedWork W2110328194 @default.
- W4283383761 hasRelatedWork W2150506001 @default.
- W4283383761 hasRelatedWork W2154859999 @default.
- W4283383761 hasRelatedWork W2378845890 @default.
- W4283383761 hasRelatedWork W2379557436 @default.
- W4283383761 hasRelatedWork W28348178 @default.
- W4283383761 hasRelatedWork W2950022897 @default.
- W4283383761 hasRelatedWork W3177279640 @default.
- W4283383761 isParatext "false" @default.
- W4283383761 isRetracted "false" @default.
- W4283383761 workType "article" @default.