CONSERVATIVELY ADAPTING A DEEP NEURAL NETWORK IN A RECOGNITION SYSTEM
摘要
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.
申请公布号
EP2965268(A2)
申请公布日期
2016.01.13
申请号
EP20140714836
申请日期
2014.03.04
申请人
MICROSOFT TECHNOLOGY LICENSING, LLC
发明人
YU, DONG;YAO, KAISHENG;SU, HANG;LI, GANG;SEIDE, FRANK