Symbolic representation of neural networks

Rudy Setiono, Huan Liu

Research output: Contribution to journalArticle

130 Citations (Scopus)

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

Fingerprint

Neural networks
Decision trees
Pattern recognition

ASJC Scopus subject areas

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

Cite this

Symbolic representation of neural networks. / Setiono, Rudy; Liu, Huan.

In: Computer, Vol. 29, No. 3, 03.1996, p. 71-77.

Research output: Contribution to journalArticle

Setiono, Rudy ; Liu, Huan. / Symbolic representation of neural networks. In: Computer. 1996 ; Vol. 29, No. 3. pp. 71-77.
@article{183467e74f5747de8f16507b47a961ce,
title = "Symbolic representation of neural networks",
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.",
author = "Rudy Setiono and Huan Liu",
year = "1996",
month = "3",
doi = "10.1109/2.485895",
language = "English (US)",
volume = "29",
pages = "71--77",
journal = "ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering",
issn = "0018-9162",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Symbolic representation of neural networks

AU - Setiono, Rudy

AU - Liu, Huan

PY - 1996/3

Y1 - 1996/3

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0030109008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030109008&partnerID=8YFLogxK

U2 - 10.1109/2.485895

DO - 10.1109/2.485895

M3 - Article

AN - SCOPUS:0030109008

VL - 29

SP - 71

EP - 77

JO - ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering

JF - ACM SIGPLAN/SIGSOFT Workshop on Program Analysis for Software Tools and Engineering

SN - 0018-9162

IS - 3

ER -