1. University of Kragujevac Digital Archive
  2. University of Kragujevac
  3. Faculty of Technical Sciences, Čačak
Please use this identifier to cite or link to this item: https://scidar.kg.ac.rs/handle/123456789/21166
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLutovac Banduka, Maja-
dc.contributor.authorPoucki, Vladimir-
dc.contributor.authorMladenovic, Vladimir-
dc.contributor.authorLutovac, Miroslav-
dc.date.accessioned2024-10-08T07:45:02Z-
dc.date.available2024-10-08T07:45:02Z-
dc.date.issued2024-
dc.identifier.isbn9788677762766en_US
dc.identifier.urihttps://scidar.kg.ac.rs/handle/123456789/21166-
dc.description.abstractIt is presented how the slope of symmetric activation functions with saturation affects class detection using symbolic analysis. Different activation functions can be used to increase the most likely detected classes. The main result is the determination of the highest slope of the activation function and the lowest slope of the activation function in terms of the number of neurons in the layer.en_US
dc.language.isoenen_US
dc.publisherFaculty of Technical Sciences Čačak, University of Kragujevacen_US
dc.relation.ispartof10th International Scientific Conference Technics, Informatics and Education - TIE 2024en_US
dc.rightsCC0 1.0 Universal*
dc.rights.urihttp://creativecommons.org/publicdomain/zero/1.0/*
dc.subjectclass detectionen_US
dc.subjectprobabilityen_US
dc.subjectautomated drawingen_US
dc.subjectsymbolic solving of the neural networken_US
dc.titleEffect of the Slope of Symmetric Saturated Activation Functions on Deep Learningen_US
dc.typeconferenceObjecten_US
dc.description.versionPublisheden_US
dc.identifier.doi10.46793/TIE24.079LBen_US
dc.type.versionPublishedVersionen_US
Appears in Collections:Faculty of Technical Sciences, Čačak

Page views(s)

123

Downloads(s)

9

Files in This Item:
File Description SizeFormat 
12 - I.10..pdf428.6 kBAdobe PDFThumbnail
View/Open
Show simple item record


This item is licensed under a Creative Commons License Creative Commons