SDTs: sparse dynamic trees

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

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
Title of host publicationArtificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
PublisherIET
Pages527-532 vol.2
Number of pages6
ISBN (Print)0-85296-721-7
DOIs
Publication statusPublished - 1999

Keywords

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

Cite this