Patent · US Active

Fast PCA method for big discrete data

US9922058B2 · kind B2 · utility

0Cited by
0References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 16, 2014
Grant dateMar 20, 2018
Priority date
Expiry dateApr 12, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F16/217
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

This disclosure is related to further approximating multiple data vectors of a dataset. The multiple data vectors are initially approximated by one or more stored principle components. A processor performs multiple iterations of determining an updated estimate of a further principle component based on the multiple data vectors that are initially approximated by the one or more stored principle components. The processor performs this step such that the updated estimate of the further principal component further approximates the dataset. In each iteration the processor constrains the updated estimate of the further principal component to be orthogonal to each of the one or more stored principal components. The data vectors of the dataset are not manipulated but remain the same data vectors that are approximated by the stored principal components.

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