Patent · US Active

Unsupervised neighbor-preserving embedding for image stream visualization and anomaly detection

US10885627B2 · kind B2 · utility

1Cited by
2References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 1, 2019
Grant dateJan 5, 2021
Priority date
Expiry dateJul 15, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and systems for detecting and correcting anomalous inputs include training a neural network to embed high-dimensional input data into a low-dimensional space with an embedding that preserves neighbor relationships. Input data items are embedded into the low-dimensional space to form respective low-dimensional codes. An anomaly is determined among the high-dimensional input data based on the low-dimensional codes. The anomaly is corrected.

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