Patent · US Expired

Automatic neural-net model generation and maintenance

US7483868B2 · kind B2 · utility

9Cited by
37References
39Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 26, 2003
Grant dateJan 27, 2009
Priority date
Expiry dateApr 30, 2025

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Method of incrementally forming and adaptively updating a neural net model are provided. A function approximation node is incrementally added to the neural net model. Function parameters for the function approximation node are determined and function parameters of other nodes in the neural network model are updated, by using the function parameters of the other nodes prior to addition of the function approximation node to the neural network model.

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