SDTs: sparse dynamic trees

N.J. Adams; C.K.I. Williams

doi:10.1049/cp:19991163

SDTs: sparse dynamic trees

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce a class of image models which we call sparse dynamic trees (SDTs). These extend our previous work (1999) on dynamic trees by introducing a top-down generative prior for the tree structures, which leads to a sparse use of nodes in the network. We present results showing the properties of these networks in action on 1D patterns

Original language	English
Title of host publication	Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
Publisher	IET
Pages	527-532 vol.2
Number of pages	6
ISBN (Print)	0-85296-721-7
DOIs	https://doi.org/10.1049/cp:19991163
Publication status	Published - 1999

Keywords

neural nets
image models
image segmentation
probability
simulated annealing
sparse dynamic trees
tree structured belief net
tree structures

Access to Document

10.1049/cp:19991163

http://digital-library.theiet.org/content/conferences/10.1049/cp_19991163

Cite this

@inproceedings{17b0b2ae7ac64cd39f8af30c7a98e673,

title = "SDTs: sparse dynamic trees",

abstract = "We introduce a class of image models which we call sparse dynamic trees (SDTs). These extend our previous work (1999) on dynamic trees by introducing a top-down generative prior for the tree structures, which leads to a sparse use of nodes in the network. We present results showing the properties of these networks in action on 1D patterns",

keywords = "neural nets, image models, image segmentation, probability, simulated annealing, sparse dynamic trees, tree structured belief net, tree structures",

author = "N.J. Adams and C.K.I. Williams",

year = "1999",

doi = "10.1049/cp:19991163",

language = "English",

isbn = "0-85296-721-7",

pages = "527--532 vol.2",

booktitle = "Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)",

publisher = "IET",

}

TY - GEN

T1 - SDTs: sparse dynamic trees

AU - Adams, N.J.

AU - Williams, C.K.I.

PY - 1999

Y1 - 1999

N2 - We introduce a class of image models which we call sparse dynamic trees (SDTs). These extend our previous work (1999) on dynamic trees by introducing a top-down generative prior for the tree structures, which leads to a sparse use of nodes in the network. We present results showing the properties of these networks in action on 1D patterns

AB - We introduce a class of image models which we call sparse dynamic trees (SDTs). These extend our previous work (1999) on dynamic trees by introducing a top-down generative prior for the tree structures, which leads to a sparse use of nodes in the network. We present results showing the properties of these networks in action on 1D patterns

KW - neural nets

KW - image models

KW - image segmentation

KW - probability

KW - simulated annealing

KW - sparse dynamic trees

KW - tree structured belief net

KW - tree structures

U2 - 10.1049/cp:19991163

DO - 10.1049/cp:19991163

M3 - Conference contribution

SN - 0-85296-721-7

SP - 527-532 vol.2

BT - Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)

PB - IET

ER -