公开(公告)号：EP3905088A1

公开(公告)日：2021-11-03

申请号：EP21151022.7

申请日：2021-01-11

申请人： Microsoft Technology Licensing, LLC

发明人： SEIDE, Frank ,  KSHIRSAGAR, Kamlesh

IPC分类号： G06F21/62 ,  G06K9/00 ,  G06K9/34 ,  G06N3/04

摘要： The technology described herein obfuscates image content using a local neural network and a remote neural network. The local network runs on a local computer system and a remote classifier runs in a remote computing system. Together, the local network and the remote classifier are able to classify images, while the image never leaves the local computer system. In aspects of the technology, the local network receives a local image and creates a transformed object. The transformed object may be generated by processing the image with a local neural network to generate a multidimensional array and then randomly shuffling data locations within a multidimensional array or deleting data. The deleting can be accomplished by multiplying the multidimensional array by a mask of deterministically arranged ones and zeros. The transformed object is communicated to the remote classifier in the remote computing system for classification.

公开(公告)号：EP2965268A2

公开(公告)日：2016-01-13

申请号：EP14714836.5

申请日：2014-03-04

申请人： Microsoft Technology Licensing, LLC

发明人： YU, Dong ,  YAO, Kaisheng ,  SU, Hang ,  LI, Gang ,  SEIDE, Frank

IPC分类号： G06N3/04 ,  G06N3/08

CPC分类号： G10L15/16 ,  G06N3/0481 ,  G06N3/084 ,  G10L15/07 ,  G10L15/20

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.