Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/111099
Title: Design Methodology of a Fully Parallelized Neural Network on a FPGA
Authors: Pérez Suárez, Santiago Tomás 
Robaina, Carlos Osorio
Vásquez Núñez, José L.
Alonso Hernández, Jesús Bernardino 
Travieso González, Carlos Manuel 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Neural Network
FPGA
Floating point
Fixed point
Matlab, et al
Issue Date: 2014
Publisher: WSEAS Press
Journal: Recent advances in electrical engineering 
Conference: 8th International Conference on Circuits, Systems, Signal and Telecommunications (CSST 2014) 
Abstract: In this work a methodology of a parallelized neural network has been designed. It explains a way to design a Neural Network using Mathworks and Xilinx Tools. Initially, the floating point algorithm was evaluated using MatlabNeural Network Toolbox. Afterwards, the fixed point algorithm was designed on a Field Programmable Gate Array (FPGA).The architecture was fully parallelized. The design tool used is System Generator of Xilinx, which works over Simulink. Finally the System Generator design is compiled for Xilinx Integrated System Environment (ISE).
URI: http://hdl.handle.net/10553/111099
ISBN: 978-960-474-359-9
ISSN: 1790-5117
Source: Proceedings of the 8th WSEAS International Conference on Circuits, Systems, Signal and Telecommunications (CSST 2014)
Appears in Collections:Actas de congresos
Adobe PDF (593,63 kB)
Show full item record

Page view(s)

22
checked on Sep 25, 2021

Download(s)

3
checked on Sep 25, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.