Patent · US Expired

Neural net architecture for rate-varying inputs

US5220640A · kind A · utility

31Cited by
6References
7Claims
0Family size

Assignee

Inventor

Key dates

Filing dateSep 20, 1990
Grant dateJun 15, 1993
Priority date
Expiry dateSep 20, 2010

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/16
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A neural net architecture provides for the recognition of an input signal which is a rate variant of a learned signal pattern, reducing the neural net training requirements. The duration of a digital sampling of the input signal is scaled by a time-scaling network, creating a multiplicity of scaled signals which are then compared to memorized signal patterns contained in a self-organizing feature map. The feature map outputs values which indicate how well the scaled input signals match various learned signal patterns. A comparator determines which one of the values is greatest, thus indicating a best match between the input signal and one of the learned signal patterns.

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