Patent · US Active

Tunable bias reduction pipeline

US11657236B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 26, 2020
Grant dateMay 23, 2023
Priority date
Expiry dateNov 25, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods may reduce bias in an artificial intelligence model. The system may receive word embedding model generated based on a corpus of words. The system may determine a bias definition vector in an embedding space of the word embedding model. The system may receive bias classification criteria. The bias classification criteria may include logic to group word vectors in the word embedding model based on a distance measurement from the bias definition vector. The system may identify, in the word embedding model, a first group of vectors and a second group of vectors based on the bias classification criteria and the bias definition vector. The system may generate a debiased artificial intelligence model. The debiased artificial intelligence model may include associations between words and metrics. The system may weight the metrics for the words associated with the first and second group of vectors with a non-zero penalization factor.

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