Fault tolerant CNN template design and optimization based on chip measurements

Peter Foldesy, Laszlo Kek, T. Roska, A. Zarándy, Guszti Bartfai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper proposes a generic method for finding non-propagating Cellular Neural Network (CNN) templates that can be implemented reliably on a given CNN Universal Machine chip. The method has two main components: (i) adaptive optimization of templates based on measurements of actual CNN chips; (ii) simplification and decomposition of Boolean operators into a sequence of simpler ones that work correctly and more robustly on a given chip. Examples are presented using two concrete stored-program CNNUM chips to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
EditorsV. Tavsanoglu
PublisherIEEE
Pages404-409
Number of pages6
Publication statusPublished - 1998
EventProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA - London, UK
Duration: Apr 14 1998Apr 17 1998

Other

OtherProceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA
CityLondon, UK
Period4/14/984/17/98

Fingerprint

Cellular neural networks
Concretes
Decomposition

ASJC Scopus subject areas

  • Software

Cite this

Foldesy, P., Kek, L., Roska, T., Zarándy, A., & Bartfai, G. (1998). Fault tolerant CNN template design and optimization based on chip measurements. In V. Tavsanoglu (Ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 404-409). IEEE.

Fault tolerant CNN template design and optimization based on chip measurements. / Foldesy, Peter; Kek, Laszlo; Roska, T.; Zarándy, A.; Bartfai, Guszti.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. ed. / V. Tavsanoglu. IEEE, 1998. p. 404-409.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Foldesy, P, Kek, L, Roska, T, Zarándy, A & Bartfai, G 1998, Fault tolerant CNN template design and optimization based on chip measurements. in V Tavsanoglu (ed.), Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 404-409, Proceedings of the 1998 5th IEEE International Workshop on Cellular Neural Networks and Their Applications, CNNA, London, UK, 4/14/98.
Foldesy P, Kek L, Roska T, Zarándy A, Bartfai G. Fault tolerant CNN template design and optimization based on chip measurements. In Tavsanoglu V, editor, Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1998. p. 404-409
Foldesy, Peter ; Kek, Laszlo ; Roska, T. ; Zarándy, A. ; Bartfai, Guszti. / Fault tolerant CNN template design and optimization based on chip measurements. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. editor / V. Tavsanoglu. IEEE, 1998. pp. 404-409
@inproceedings{700924789fc74503b5bf3ee5a7f8e08d,
title = "Fault tolerant CNN template design and optimization based on chip measurements",
abstract = "This paper proposes a generic method for finding non-propagating Cellular Neural Network (CNN) templates that can be implemented reliably on a given CNN Universal Machine chip. The method has two main components: (i) adaptive optimization of templates based on measurements of actual CNN chips; (ii) simplification and decomposition of Boolean operators into a sequence of simpler ones that work correctly and more robustly on a given chip. Examples are presented using two concrete stored-program CNNUM chips to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.",
author = "Peter Foldesy and Laszlo Kek and T. Roska and A. Zar{\'a}ndy and Guszti Bartfai",
year = "1998",
language = "English",
pages = "404--409",
editor = "V. Tavsanoglu",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - Fault tolerant CNN template design and optimization based on chip measurements

AU - Foldesy, Peter

AU - Kek, Laszlo

AU - Roska, T.

AU - Zarándy, A.

AU - Bartfai, Guszti

PY - 1998

Y1 - 1998

N2 - This paper proposes a generic method for finding non-propagating Cellular Neural Network (CNN) templates that can be implemented reliably on a given CNN Universal Machine chip. The method has two main components: (i) adaptive optimization of templates based on measurements of actual CNN chips; (ii) simplification and decomposition of Boolean operators into a sequence of simpler ones that work correctly and more robustly on a given chip. Examples are presented using two concrete stored-program CNNUM chips to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.

AB - This paper proposes a generic method for finding non-propagating Cellular Neural Network (CNN) templates that can be implemented reliably on a given CNN Universal Machine chip. The method has two main components: (i) adaptive optimization of templates based on measurements of actual CNN chips; (ii) simplification and decomposition of Boolean operators into a sequence of simpler ones that work correctly and more robustly on a given chip. Examples are presented using two concrete stored-program CNNUM chips to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=0031638972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031638972&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031638972

SP - 404

EP - 409

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

A2 - Tavsanoglu, V.

PB - IEEE

ER -