Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/45CGCM8
Repositorysid.inpe.br/sibgrapi/2021/09.04.01.58
Last Update2021:09.04.01.58.26 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2021/09.04.01.58.26
Metadata Last Update2022:06.14.00.00.24 (UTC) administrator
DOI10.1109/SIBGRAPI54419.2021.00059
Citation KeySousaFernVasc:2021:NoSeNe
TitleConformalLayers: A non-linear sequential neural network with associative layers
FormatOn-line
Year2021
Access Date2024, May 06
Number of Files1
Size5705 KiB
2. Context
Author1 Sousa, Eduardo Vera
2 Fernandes, Leandro A. F.
3 Vasconcelos, Cristina Nader
Affiliation1 Universidade Federal Fluminense 
2 Universidade Federal Fluminense 
3 Universidade Federal Fluminense
EditorPaiva, Afonso
Menotti, David
Baranoski, Gladimir V. G.
Proença, Hugo Pedro
Junior, Antonio Lopes Apolinario
Papa, João Paulo
Pagliosa, Paulo
dos Santos, Thiago Oliveira
e Sá, Asla Medeiros
da Silveira, Thiago Lopes Trugillo
Brazil, Emilio Vital
Ponti, Moacir A.
Fernandes, Leandro A. F.
Avila, Sandra
e-Mail Addresseduardovera@ic.uff.br
Conference NameConference on Graphics, Patterns and Images, 34 (SIBGRAPI)
Conference LocationGramado, RS, Brazil (virtual)
Date18-22 Oct. 2021
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2021-09-04 01:58:26 :: eduardovera@ic.uff.br -> administrator ::
2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021
2022-03-02 13:39:09 :: menottid@gmail.com -> administrator :: 2021
2022-06-14 00:00:24 :: administrator -> :: 2021
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordsconvolutional neural network
non-linear activation
associativity
AbstractConvolutional Neural Networks (CNNs) have been widely applied. But as the CNNs grow, the number of arithmetic operations and memory footprint also increases. Furthermore, typical non-linear activation functions do not allow associativity of the operations encoded by consecutive layers, preventing the simplification of intermediate steps by combining them. We present a new activation function that allows associativity between sequential layers of CNNs. Even though our activation function is non-linear, it can be represented by a sequence of linear operations in the conformal model for Euclidean geometry. In this domain, operations like, but not limited to, convolution, average pooling, and dropout remain linear. We take advantage of associativity to combine all the "conformal layers" and make the cost of inference constant regardless of the depth of the network.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2021 > ConformalLayers: A non-linear...
Arrangement 2urlib.net > ConformalLayers: A non-linear...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 03/09/2021 22:58 1.3 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/45CGCM8
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/45CGCM8
Languageen
Target FileMain.pdf
User Groupeduardovera@ic.uff.br
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/45PQ3RS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2021/11.12.11.46 5
sid.inpe.br/sibgrapi/2022/06.10.21.49 3
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume


Close