ML Anthology

Substructure Discovery Using Minimum Description Length Principle and Background Knowledge

Surnjani Djoko
AAAI 1994 pp. 1442
/aaai/1994/djoko1994aaai-substructure/

Abstract

djoko @ cse.uta.edu Discovering conceptually interesting and repetitive substruc-tures in a structural data improves the ability to interpret and compress the data. The substructures are evaluated by their ability to describe and compress the original data set using the domain’s background knowledge and the minimum description length (MDL) of the data. Once discovered, the substructure concept is used to simplify the data by replacing instances of the substructure with a pointer to the newly dis-covered concept. The discovered substructure concepts allow abstraction over detailed structure in the original data. Iteration of the substructure discovery and replacement pro-cess constructs a hierarchical description of the structural data in terms of the discovered substructures. This hierarchy

PDF AAAI Semantic Scholar

Cite

Text

Djoko. "Substructure Discovery Using Minimum Description Length Principle and Background Knowledge." AAAI Conference on Artificial Intelligence, 1994.

Markdown

[Djoko. "Substructure Discovery Using Minimum Description Length Principle and Background Knowledge." AAAI Conference on Artificial Intelligence, 1994.](https://mlanthology.org/aaai/1994/djoko1994aaai-substructure/)

BibTeX

@inproceedings{djoko1994aaai-substructure,
  title     = {{Substructure Discovery Using Minimum Description Length Principle and Background Knowledge}},
  author    = {Djoko, Surnjani},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1994},
  pages     = {1442},
  url       = {https://mlanthology.org/aaai/1994/djoko1994aaai-substructure/}
}