Patent · US Expired

Translation of a neural network into a rule-based expert system

US5438644A · kind A · utility

40Cited by
14References
18Claims
0Family size

Assignee

Inventor

Key dates

Filing dateSep 9, 1991
Grant dateAug 1, 1995
Priority date
Expiry dateSep 9, 2011

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/042
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A rule-based expert system is generated from a neural network. The neural network is trained in such a way as to avoid redundancy and to select input weights to the various processing elements in such a way as to nullify the input weights which have smaller absolute values. The neural network is translated into a set of rules by a heuristic search technique. Additionally, the translation distinguishes between positive and negative attributes for efficiency and can adequately explore rule size exponential with a given parameter. Both explicit and implicit knowledge of adapted neural networks are decoded and represented as if--then rules.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.