公开(公告)号：US20210279635A1

公开(公告)日：2021-09-09

申请号：US16810123

申请日：2020-03-05

Applicant: QUALCOMM Incorporated

Inventor： Serag GADELRAB ,  Karamvir CHATHA ,  Ofer ROSENBERG

IPC: G06N20/00 ,  G06N5/04 ,  G06F11/34

Abstract: Certain aspects of the present disclosure provide techniques for adaptively executing machine learning models on a computing device. An example method generally includes receiving weight information for a machine learning model to be executed on a computing device. The received weight information is reduced into quantized weight information having a reduced bit size relative to the received weight information. First inferences using the machine learning model and the received weight information, and second inferences are performed using the machine learning model and the quantized weight information. Results of the first and second inferences are compared, it is determined that results of the second inferences are within a threshold performance level of results of the first inferences, and based on the determination, one or more subsequent inferences are performed using the machine learning model and the quantized weight information.

公开(公告)号：US20180218256A1

公开(公告)日：2018-08-02

申请号：US15422938

申请日：2017-02-02

Applicant: QUALCOMM Incorporated

Inventor： Dolev RAVIV ,  Ofer ROSENBERG ,  Lee SUSMAN

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/088 ,  G06N3/0454

Abstract: A method for generating synthetic behavior samples with a behavior generator includes drawing, at the behavior generator, a vector from a probability distribution obtained from behavior data of a plurality of users. The method also includes generating, with an artificial neural network decoder of the behavior generator, a synthetic behavior sample based on the vector. The method further includes tuning a model, which identifies a device user, using the generated synthetic behavior sample.

公开(公告)号：US20180189466A1

公开(公告)日：2018-07-05

申请号：US15394551

申请日：2016-12-29

Applicant: QUALCOMM Incorporated

Inventor： Dolev RAVIV ,  Lee SUSMAN ,  Ofer ROSENBERG

IPC: G06F21/31 ,  G06N3/08

CPC classification number: G06F21/316 ,  G06N3/08

Abstract: A method of authenticating a user on a mobile device includes gathering samples of behavioral data of the user from multiple sensors of the mobile device, each sensor generating a different number of samples. The method also includes normalizing the samples to have a same number of samples for each sensor. The method further includes extracting, with a convolutional neural network, features from the normalized samples and authenticating the user based on the extracted features.