English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/84753
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:


Red neuronal convolucional rápida sin fotogramas para reconocimientos de dígitos

AuthorsPerez-Carrasco, J. A.; Serrano-Gotarredona, Carmen; Acha Piñero, Begoña; Serrano-Gotarredona, Teresa ; Linares-Barranco, Bernabé
Issue Date2011
PublisherUnión Científica Internacional de Radio
CitationXXVI Simposio de la URSI (2011)
AbstractIn this paper a bio-inspired six-layer convolutional network (ConvNet) non-frame based for digit recognition is shown. The system has been trained with the backpropagation algorithm using 32x32 images from the MNIST database. The system can be implemented with already physically available spike-based electronic devices. 10000 images have been coded into events separated 50ns to test the non-frame based ConvNet system. The simulation results have been obtained using actual performance figures for existing AER (Address Event Representation) hardware components. We provide simulation results of the system showing recognition delays of a few microseconds from stimulus onset with a recognition rate of 93%. The complete system consists of 30 convolution modules.
DescriptionComunicación presentada al "XXVI Simposio de la URSI" celebrado en Leganés (España) del 7 al 9 de Septiembre del 2011.
Publisher version (URL)http://www.ursi2011.org/index.htm
Appears in Collections:(IMSE-CNM) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
RED NEURONAL.pdf275,12 kBAdobe PDFThumbnail
Show full item record
Review this work

WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.