Design graph search problems with learning: A neural network approach

Gee Gwo Mei; Wentai Liu; Su shing Chen

doi:10.1016/0893-6080(88)90237-7

Design graph search problems with learning: A neural network approach

Gee Gwo Mei, Wentai Liu, Su shing Chen

Department of Biomedical Engineering

Research output: Contribution to journal › Conference article › peer-review

Abstract

One of the problem in the algorithm design is whether algorithms can be designed in a collective and adaptive manner instead of individually developing each algorithm. The motivation of this paper is the study of a cognitive process, in the content of neural network model, which allows us to systematically modify an existing algorithm into a new algorithm. Algorithm design is formulated as a process of successive planning and constraint manipulation. The original problem is continuously decomposed and refined into a hierarchical level of realizable subproblems.

Original language	English
Pages (from-to)	200
Number of pages	1
Journal	Neural Networks
Volume	1
Issue number	1 SUPPL
DOIs	https://doi.org/10.1016/0893-6080(88)90237-7
Publication status	Published - 1988
Event	International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: 1988 Sept 6 → 1988 Sept 10

All Science Journal Classification (ASJC) codes

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/0893-6080(88)90237-7

Cite this

@article{0107afd758b44d25804c70afb3c7dc52,

title = "Design graph search problems with learning: A neural network approach",

abstract = "One of the problem in the algorithm design is whether algorithms can be designed in a collective and adaptive manner instead of individually developing each algorithm. The motivation of this paper is the study of a cognitive process, in the content of neural network model, which allows us to systematically modify an existing algorithm into a new algorithm. Algorithm design is formulated as a process of successive planning and constraint manipulation. The original problem is continuously decomposed and refined into a hierarchical level of realizable subproblems.",

author = "Mei, {Gee Gwo} and Wentai Liu and Chen, {Su shing}",

year = "1988",

doi = "10.1016/0893-6080(88)90237-7",

language = "English",

volume = "1",

pages = "200",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "1 SUPPL",

note = "International Neural Network Society 1988 First Annual Meeting ; Conference date: 06-09-1988 Through 10-09-1988",

}

TY - JOUR

T1 - Design graph search problems with learning

T2 - International Neural Network Society 1988 First Annual Meeting

AU - Mei, Gee Gwo

AU - Liu, Wentai

AU - Chen, Su shing

PY - 1988

Y1 - 1988

N2 - One of the problem in the algorithm design is whether algorithms can be designed in a collective and adaptive manner instead of individually developing each algorithm. The motivation of this paper is the study of a cognitive process, in the content of neural network model, which allows us to systematically modify an existing algorithm into a new algorithm. Algorithm design is formulated as a process of successive planning and constraint manipulation. The original problem is continuously decomposed and refined into a hierarchical level of realizable subproblems.

AB - One of the problem in the algorithm design is whether algorithms can be designed in a collective and adaptive manner instead of individually developing each algorithm. The motivation of this paper is the study of a cognitive process, in the content of neural network model, which allows us to systematically modify an existing algorithm into a new algorithm. Algorithm design is formulated as a process of successive planning and constraint manipulation. The original problem is continuously decomposed and refined into a hierarchical level of realizable subproblems.

UR - http://www.scopus.com/inward/record.url?scp=0024168037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024168037&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90237-7

DO - 10.1016/0893-6080(88)90237-7

M3 - Conference article

AN - SCOPUS:0024168037

SN - 0893-6080

VL - 1

SP - 200

JO - Neural Networks

JF - Neural Networks

IS - 1 SUPPL

Y2 - 6 September 1988 through 10 September 1988

ER -

Design graph search problems with learning: A neural network approach

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this