Advanced

In search of a robust digital CNN system

Fang, Wen Hai LU ; Wang, Cheng and Spaanenburg, Lambert LU (2006) 10th International Workshop on Cellular Neural Networks and their Applications (CNNA) In Proceedings of the 2006 10th IEEE International Workshop on Cellular Neural Networks and Their Applications p.328-333
Abstract
Microelectronics promises a high component density and low power dissipation to embedded systems. Unfortunately such a component will always suffer from various error types that make the chip respond differently from its functional simulation. This is especially true for Cellular Neural Networks (CNN), which makes the determination of robust, low-precision parameters to guarantee small footprint and reliable operation an important design consideration. This paper describes the digital word width effects in a CNN implementation that must be considered to achieve a small size for a reliable system. It discusses the automated design space exploration using a Field-Programmable Gate-Array (FPGA) implementation to perform an optimal CNN... (More)
Microelectronics promises a high component density and low power dissipation to embedded systems. Unfortunately such a component will always suffer from various error types that make the chip respond differently from its functional simulation. This is especially true for Cellular Neural Networks (CNN), which makes the determination of robust, low-precision parameters to guarantee small footprint and reliable operation an important design consideration. This paper describes the digital word width effects in a CNN implementation that must be considered to achieve a small size for a reliable system. It discusses the automated design space exploration using a Field-Programmable Gate-Array (FPGA) implementation to perform an optimal CNN parameters selection. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
automated design space exploration, digital word width effects, cellular neural networks, microelectronics, robust templates, embedded systems, field-programmable gate-array
in
Proceedings of the 2006 10th IEEE International Workshop on Cellular Neural Networks and Their Applications
pages
6 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
10th International Workshop on Cellular Neural Networks and their Applications (CNNA)
external identifiers
  • WOS:000245392200070
  • Scopus:47549086536
ISBN
1-4244-0639-0
DOI
10.1109/CNNA.2006.341654
language
English
LU publication?
yes
id
ac2bd5b0-6226-4b8c-bd01-099d537be380 (old id 1409811)
date added to LUP
2007-11-24 13:02:55
date last changed
2016-10-13 04:39:40
@misc{ac2bd5b0-6226-4b8c-bd01-099d537be380,
  abstract     = {Microelectronics promises a high component density and low power dissipation to embedded systems. Unfortunately such a component will always suffer from various error types that make the chip respond differently from its functional simulation. This is especially true for Cellular Neural Networks (CNN), which makes the determination of robust, low-precision parameters to guarantee small footprint and reliable operation an important design consideration. This paper describes the digital word width effects in a CNN implementation that must be considered to achieve a small size for a reliable system. It discusses the automated design space exploration using a Field-Programmable Gate-Array (FPGA) implementation to perform an optimal CNN parameters selection.},
  author       = {Fang, Wen Hai and Wang, Cheng and Spaanenburg, Lambert},
  isbn         = {1-4244-0639-0},
  keyword      = {automated design space exploration,digital word width effects,cellular neural networks,microelectronics,robust templates,embedded systems,field-programmable gate-array},
  language     = {eng},
  pages        = {328--333},
  publisher    = {ARRAY(0x7cde808)},
  series       = {Proceedings of the 2006 10th IEEE International Workshop on Cellular Neural Networks and Their Applications},
  title        = {In search of a robust digital CNN system},
  url          = {http://dx.doi.org/10.1109/CNNA.2006.341654},
  year         = {2006},
}