Patent · US Active

Sensor transformation attention network (STAN) model

US11501154B2 · kind B2 · utility

0Cited by

5References

22Claims

0Family size

Assignees

SAMSUNG ELECTRONICS CO., LTD. · KR
UNIVERSITAET ZUERICH · CH

Inventors

Stefan Braun · Blankenloch, DE
Daniel Neil · Zürich, CH
Enea Ceolini · New York, US
Jithendar Anumula · Berlin, DE
Shih-Chii Liu · Zürich, CH

Key dates

Filing date	Mar 5, 2018
Grant date	Nov 15, 2022
Priority date	—
Expiry date	Sep 16, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/24
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A sensor transformation attention network (STAN) model including sensors, attention modules, a merge module and a task-specific module is provided. The attention modules calculate attention scores of feature vectors corresponding to the input signals collected by the sensors. The merge module calculates attention values of the attention scores, and generates a merged transformation vector based on the attention values and the feature vectors. The task-specific module classifies the merged transformation vector.

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