Translation of a neural network into a rule-based expert system
US5438644A · kind A · utility
Assignee
Inventor
Key dates
| Filing date | Sep 9, 1991 |
| Grant date | Aug 1, 1995 |
| Priority date | — |
| Expiry date | Sep 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.