Patent · US Expired

Rapidly trainable neural tree network

US5634087A · kind A · utility

61Cited by
14References
61Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 29, 1993
Grant dateMay 27, 1997
Priority date
Expiry dateNov 29, 2013

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/24323
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An apparatus and methods characterized by an electric neural network including a node having multipliers respectively receiving signals representing feature vector elements and signals representing weight vector elements to produce product signals, a summer to add the product signals with a bias signal and output a sum signal to a hard limiter, the hard limiter for outputting a preliminary output signal of polarity. In response to the output signal of polarity, one of at least two logic branches is enabled. In response to such enabling, weight elements are assigned to a next weight vector to be used in subsequent processing by the one of the at least two logic branches until a label is to be produced.

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