Optimal path finding with space variant metric weights via multilayer CNN-UM

H. Kim, Y. Park, T. Roska, L. O. Chua

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

2 Citations (Scopus)

Abstract

Analogic CNN-based optimal path finding algorithm is proposed to solve the problem with space variant metric weights. The algorithm is based on the analog version of modified dynamic programming which is implemented with nonlinear templates on the multi-layer CNN-UM. The structure is composed of distance computing layer, intermediate layer, and path finding layer. Employment of intermediate layers allows the space variant distance weights to be provided externally and the CNN structure to be compact.

Original languageEnglish
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Pages429-432
Number of pages4
Volume3
Publication statusPublished - 2001
EventIEEE International Symposium on Circuits and Systems (ISCAS 2001) - Sydney, NSW, Australia
Duration: May 6 2001May 9 2001

Other

OtherIEEE International Symposium on Circuits and Systems (ISCAS 2001)
CountryAustralia
CitySydney, NSW
Period5/6/015/9/01

Fingerprint

Multilayers
Dynamic programming

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Hardware and Architecture

Cite this

Kim, H., Park, Y., Roska, T., & Chua, L. O. (2001). Optimal path finding with space variant metric weights via multilayer CNN-UM. In Proceedings - IEEE International Symposium on Circuits and Systems (Vol. 3, pp. 429-432)

Optimal path finding with space variant metric weights via multilayer CNN-UM. / Kim, H.; Park, Y.; Roska, T.; Chua, L. O.

Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 3 2001. p. 429-432.

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

Kim, H, Park, Y, Roska, T & Chua, LO 2001, Optimal path finding with space variant metric weights via multilayer CNN-UM. in Proceedings - IEEE International Symposium on Circuits and Systems. vol. 3, pp. 429-432, IEEE International Symposium on Circuits and Systems (ISCAS 2001), Sydney, NSW, Australia, 5/6/01.
Kim H, Park Y, Roska T, Chua LO. Optimal path finding with space variant metric weights via multilayer CNN-UM. In Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 3. 2001. p. 429-432
Kim, H. ; Park, Y. ; Roska, T. ; Chua, L. O. / Optimal path finding with space variant metric weights via multilayer CNN-UM. Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 3 2001. pp. 429-432
@inproceedings{a04e783d61fb4e79a11f8623918303dc,
title = "Optimal path finding with space variant metric weights via multilayer CNN-UM",
abstract = "Analogic CNN-based optimal path finding algorithm is proposed to solve the problem with space variant metric weights. The algorithm is based on the analog version of modified dynamic programming which is implemented with nonlinear templates on the multi-layer CNN-UM. The structure is composed of distance computing layer, intermediate layer, and path finding layer. Employment of intermediate layers allows the space variant distance weights to be provided externally and the CNN structure to be compact.",
author = "H. Kim and Y. Park and T. Roska and Chua, {L. O.}",
year = "2001",
language = "English",
volume = "3",
pages = "429--432",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

}

TY - GEN

T1 - Optimal path finding with space variant metric weights via multilayer CNN-UM

AU - Kim, H.

AU - Park, Y.

AU - Roska, T.

AU - Chua, L. O.

PY - 2001

Y1 - 2001

N2 - Analogic CNN-based optimal path finding algorithm is proposed to solve the problem with space variant metric weights. The algorithm is based on the analog version of modified dynamic programming which is implemented with nonlinear templates on the multi-layer CNN-UM. The structure is composed of distance computing layer, intermediate layer, and path finding layer. Employment of intermediate layers allows the space variant distance weights to be provided externally and the CNN structure to be compact.

AB - Analogic CNN-based optimal path finding algorithm is proposed to solve the problem with space variant metric weights. The algorithm is based on the analog version of modified dynamic programming which is implemented with nonlinear templates on the multi-layer CNN-UM. The structure is composed of distance computing layer, intermediate layer, and path finding layer. Employment of intermediate layers allows the space variant distance weights to be provided externally and the CNN structure to be compact.

UR - http://www.scopus.com/inward/record.url?scp=0035011626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035011626&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 429

EP - 432

BT - Proceedings - IEEE International Symposium on Circuits and Systems

ER -