Learning through failure

Authors Taisuke Sato, Yoshitaka Kameya



PDF
Thumbnail PDF

File

DagSemProc.05051.9.pdf
  • Filesize: 150 kB
  • 6 pages

Document Identifiers

Author Details

Taisuke Sato
Yoshitaka Kameya

Cite AsGet BibTex

Taisuke Sato and Yoshitaka Kameya. Learning through failure. In Probabilistic, Logical and Relational Learning - Towards a Synthesis. Dagstuhl Seminar Proceedings, Volume 5051, pp. 1-6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2006)
https://doi.org/10.4230/DagSemProc.05051.9

Abstract

PRISM, a symbolic-statistical modeling language we have been developing since '97, recently incorporated a program transformation technique to handle failure in generative modeling. I'll show this feature opens a way to new breeds of symbolic models, including EM learning from negative observations, constrained HMMs and finite PCFGs.
Keywords
  • Program transformation
  • failure
  • generative modeling

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads