Patent · US Active

Training machine-learned models for perceptual tasks using biometric data

US11823439B2 · kind B2 · utility

0Cited by
8References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 16, 2020
Grant dateNov 21, 2023
Priority date
Expiry dateJul 30, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2218/12
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Generally, the present disclosure is directed to systems and methods that train machine-learned models (e.g., artificial neural networks) to perform perceptual or cognitive task(s) based on biometric data (e.g., brain wave recordings) collected from living organism(s) while the living organism(s) are performing the perceptual or cognitive task(s). In particular, aspects of the present disclosure are directed to a new supervision paradigm, by which machine-learned feature extraction models are trained using example stimuli paired with companion biometric data such as neural activity recordings (e g electroencephalogram data, electrocorticography data, functional near-infrared spectroscopy, and/or magnetoencephalography data) collected from a living organism (e.g., human being) while the organism perceived those examples (e.g., viewing the image, listening to the speech, etc.).

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