ML Anthology

Unification as Constraint Satisfaction in Structured Connectionist Networks

Andreas Stolcke
NeCo 1989 pp. 559-567
doi:10.1162/NECO.1989.1.4.559 /neco/1989/stolcke1989neco-unification/

Abstract

Unification is a basic concept in several traditional symbolic formalisms that should be well suited for a connectionist implementation due to the intuitive nature of the notions it formalizes. It is shown that by approaching unification from a graph matching and constraint satisfaction perspective a natural and efficient realization in a structured connectionist network can be found.

PDF NeCo Semantic Scholar

Cite

Text

Stolcke. "Unification as Constraint Satisfaction in Structured Connectionist Networks." Neural Computation, 1989. doi:10.1162/NECO.1989.1.4.559

Markdown

[Stolcke. "Unification as Constraint Satisfaction in Structured Connectionist Networks." Neural Computation, 1989.](https://mlanthology.org/neco/1989/stolcke1989neco-unification/) doi:10.1162/NECO.1989.1.4.559

BibTeX

@article{stolcke1989neco-unification,
  title     = {{Unification as Constraint Satisfaction in Structured Connectionist Networks}},
  author    = {Stolcke, Andreas},
  journal   = {Neural Computation},
  year      = {1989},
  pages     = {559-567},
  doi       = {10.1162/NECO.1989.1.4.559},
  volume    = {1},
  url       = {https://mlanthology.org/neco/1989/stolcke1989neco-unification/}
}