Matches in SemOpenAlex for { <https://semopenalex.org/work/W2591824675> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2591824675 abstract "The Maxout network is an alternative to artificial neural networks that use fixed activation functions. By adding extra layers of linear nodes the Maxout network is able to learn both the relationship between the hidden nodes and the activation function that they use. The idea was presented as a natural companion to the dropout technique when training large convolutional networks, showing state-of-the-art results on several benchmark datasets. In this project we apply the Maxout method, without dropout, as a substitute to a sigmoidal activation function used in small networks with only one hidden layer. We show that the Maxout method can improve the performance of some classification problems while also decreasing the computer run-time needed for training. The classification problems used were artificially created to be non-linear multi-dimensional problems. The Maxout method was also tested on a highly complex regression problem and showed to yield as good results as the sigmoidal activation function, while taking a lot shorter time to train. (Less)" @default.
- W2591824675 created "2017-03-16" @default.
- W2591824675 creator A5015722096 @default.
- W2591824675 date "2016-01-01" @default.
- W2591824675 modified "2023-09-27" @default.
- W2591824675 title "Applying the Maxout Model to Increase the Performance of the Multilayer Perceptron in Shallow Networks" @default.
- W2591824675 cites W2158698691 @default.
- W2591824675 cites W2166116275 @default.
- W2591824675 hasPublicationYear "2016" @default.
- W2591824675 type Work @default.
- W2591824675 sameAs 2591824675 @default.
- W2591824675 citedByCount "0" @default.
- W2591824675 crossrefType "journal-article" @default.
- W2591824675 hasAuthorship W2591824675A5015722096 @default.
- W2591824675 hasConcept C108583219 @default.
- W2591824675 hasConcept C119857082 @default.
- W2591824675 hasConcept C13280743 @default.
- W2591824675 hasConcept C14036430 @default.
- W2591824675 hasConcept C154945302 @default.
- W2591824675 hasConcept C179717631 @default.
- W2591824675 hasConcept C185798385 @default.
- W2591824675 hasConcept C205649164 @default.
- W2591824675 hasConcept C2776145597 @default.
- W2591824675 hasConcept C38365724 @default.
- W2591824675 hasConcept C41008148 @default.
- W2591824675 hasConcept C50644808 @default.
- W2591824675 hasConcept C60908668 @default.
- W2591824675 hasConcept C78458016 @default.
- W2591824675 hasConcept C81363708 @default.
- W2591824675 hasConcept C81388566 @default.
- W2591824675 hasConcept C86803240 @default.
- W2591824675 hasConceptScore W2591824675C108583219 @default.
- W2591824675 hasConceptScore W2591824675C119857082 @default.
- W2591824675 hasConceptScore W2591824675C13280743 @default.
- W2591824675 hasConceptScore W2591824675C14036430 @default.
- W2591824675 hasConceptScore W2591824675C154945302 @default.
- W2591824675 hasConceptScore W2591824675C179717631 @default.
- W2591824675 hasConceptScore W2591824675C185798385 @default.
- W2591824675 hasConceptScore W2591824675C205649164 @default.
- W2591824675 hasConceptScore W2591824675C2776145597 @default.
- W2591824675 hasConceptScore W2591824675C38365724 @default.
- W2591824675 hasConceptScore W2591824675C41008148 @default.
- W2591824675 hasConceptScore W2591824675C50644808 @default.
- W2591824675 hasConceptScore W2591824675C60908668 @default.
- W2591824675 hasConceptScore W2591824675C78458016 @default.
- W2591824675 hasConceptScore W2591824675C81363708 @default.
- W2591824675 hasConceptScore W2591824675C81388566 @default.
- W2591824675 hasConceptScore W2591824675C86803240 @default.
- W2591824675 hasLocation W25918246751 @default.
- W2591824675 hasOpenAccess W2591824675 @default.
- W2591824675 hasPrimaryLocation W25918246751 @default.
- W2591824675 hasRelatedWork W1514707188 @default.
- W2591824675 hasRelatedWork W169576766 @default.
- W2591824675 hasRelatedWork W2407024328 @default.
- W2591824675 hasRelatedWork W246564837 @default.
- W2591824675 hasRelatedWork W2554486837 @default.
- W2591824675 hasRelatedWork W2766585573 @default.
- W2591824675 hasRelatedWork W2888671600 @default.
- W2591824675 hasRelatedWork W2917237312 @default.
- W2591824675 hasRelatedWork W2963012631 @default.
- W2591824675 hasRelatedWork W2977982891 @default.
- W2591824675 hasRelatedWork W3015919103 @default.
- W2591824675 hasRelatedWork W3016747886 @default.
- W2591824675 hasRelatedWork W3016986506 @default.
- W2591824675 hasRelatedWork W3122190249 @default.
- W2591824675 hasRelatedWork W3162022485 @default.
- W2591824675 hasRelatedWork W3170224572 @default.
- W2591824675 hasRelatedWork W3201541172 @default.
- W2591824675 hasRelatedWork W2926324512 @default.
- W2591824675 hasRelatedWork W3015219745 @default.
- W2591824675 hasRelatedWork W3186362161 @default.
- W2591824675 isParatext "false" @default.
- W2591824675 isRetracted "false" @default.
- W2591824675 magId "2591824675" @default.
- W2591824675 workType "article" @default.