Patent · US Active

Conservatively adapting a deep neural network in a recognition system

US9177550B2 · kind B2 · utility

16Cited by

2References

20Claims

0Family size

Assignee

MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

Dong-Sheng Yu · Ottawa, CA
Kaisheng Yao · Newcastle, US
Hang Su · Vienna, US
Gang Li · Beijing, CN
Frank Torsten Bernd Seide · Aachen, DE

Key dates

Filing date	Mar 6, 2013
Grant date	Nov 3, 2015
Priority date	—
Expiry date	Oct 20, 2033

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/20
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Various technologies described herein pertain to conservatively adapting a deep neural network (DNN) in a recognition system for a particular user or context. A DNN is employed to output a probability distribution over models of context-dependent units responsive to receipt of captured user input. The DNN is adapted for a particular user based upon the captured user input, wherein the adaption is undertaken conservatively such that a deviation between outputs of the adapted DNN and the unadapted DNN is constrained.

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