公开(公告)号：US20220101133A1

公开(公告)日：2022-03-31

申请号：US17488261

申请日：2021-09-28

Applicant: QUALCOMM Incorporated

Inventor： Randy ARDYWIBOWO ,  Venkata Ravi Kiran DAYANA ,  Hau HWANG

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A method performed by a deep neural network (DNN) includes receiving, at a layer of the DNN during an inference stage, a layer input comprising content associated with a DNN input received at the DNN. The method also includes quantizing one or more parameters of a plurality of parameters associated with the layer based on the content of the layer input. The method further includes performing a task corresponding to the DNN input, the task performed with the one or more one quantized parameters.