Symbolic representation of neural networks

Rudy Setiono, Huan Liu

Research output: Contribution to journalArticle

133 Scopus citations

Abstract

Neural networks often surpass decision trees in predicting pattern classifications, but their predictions cannot be explained. This algorithm's symbolic representations make each prediction explicit and understandable.

Original languageEnglish (US)
Pages (from-to)71-77
Number of pages7
JournalComputer
Volume29
Issue number3
DOIs
StatePublished - Mar 1996
Externally publishedYes

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Graphics and Computer-Aided Design
  • Software

Fingerprint Dive into the research topics of 'Symbolic representation of neural networks'. Together they form a unique fingerprint.

  • Cite this