1. Identity statement | |
Reference Type | Other (Misc) |
Site | sibgrapi.sid.inpe.br |
Identifier | 8JMKD3MGPEW34M/45CGCRL |
Repository | sid.inpe.br/sibgrapi/2021/09.04.02.00 |
Last Update | 2021:09.04.02.00.40 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.04.02.00.40 |
Metadata Last Update | 2022:05.15.22.30.28 (UTC) administrator |
Citation Key | SousaFernVasc:2021:NoSeNe |
Title | ConformalLayers: A non-linear sequential neural network with associative layers |
Short Title | Supplemerntary material |
Format | On-line |
Year | 2021 |
Date | 18-22 Oct. 2021 |
Access Date | 2024, May 19 |
Number of Files | 1 |
Size | 490 KiB |
|
2. Context | |
Author | 1 Sousa, Eduardo Vera 2 Fernandes, Leandro A. F. 3 Vasconcelos, Cristina Nader |
Affiliation | 1 Universidade Federal Fluminense 2 Universidade Federal Fluminense 3 Universidade Federal Fluminense |
e-Mail Address | eduardovera@ic.uff.br |
History (UTC) | 2021-09-04 02:00:40 :: eduardovera@ic.uff.br -> administrator :: 2022-05-15 22:30:28 :: administrator -> eduardovera@ic.uff.br :: 2021 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | convolutional neural network non-linear activation associativity |
Abstract | Convolutional 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 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > ConformalLayers: A non-linear... > Supplemerntary material |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > ConformalLayers: A non-linear... > Supplemerntary material |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPEW34M/45CGCRL |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45CGCRL |
Language | en |
Target File | SupplementaryMaterial.pdf |
User Group | eduardovera@ic.uff.br |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/45CGCM8 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist area callnumber city contenttype copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode howpublished isbn issn label lineage mark nextedition notes number numberofpages orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype session sponsor subject tertiarymark tertiarytype type url versiontype |
|
7. Description control | |
e-Mail (login) | eduardovera@ic.uff.br |
update | |
|