Patent · US Expired

Discriminant neural networks

US5926804A · kind A · utility

18Cited by
3References
6Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 1, 1994
Grant dateJul 20, 1999
Priority date
Expiry dateJul 1, 2014

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A discriminant neural network and a method of training the network are disclosed. The network includes a set of hidden nodes having associated weights, and the number of hidden nodes is minimized by the training method of the invention. The training method includes the steps of 1) loading a training data set and assigning it to a residual data set, 2) computing a vector associated with a first hidden node using the residual data set, 3) projecting training data onto a hyperplane associated with said first hidden node, 4) determining the number and locations of hard-limiter thresholds associated with the first node, and 5) repeating the above for successive hidden nodes after removing satisfied subsets from the training data until all partitioned regions of the input data space are satisfied.

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