公开(公告)号：US20170308324A1

公开(公告)日：2017-10-26

申请号：US15137543

申请日：2016-04-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Vanessa COURVILLE ,  Manuel SALDANA ,  Barnaby DALTON

IPC: G06F3/06 ,  G06N3/08

CPC classification number: G06F3/0656 ,  G06F3/0608 ,  G06F3/0673 ,  G06N3/0454 ,  G06N3/084

Abstract: A circuit for a multistage sequential data process includes a plurality of memory units. Each memory unit is associated with a stage of the sequential data process which, for each data set inputted to the stage, the stage provides an intermediate data set for storage in the associated memory unit for use in at least one subsequent stage of the sequential data process, where each of the plurality of memory units is sized based on relative locations of the stage providing the intermediate data set and the at least one subsequent stage in the sequential data process.

公开(公告)号：US20240070221A1

公开(公告)日：2024-02-29

申请号：US18502506

申请日：2023-11-06

Applicant: Huawei Technologies Co., Ltd.

Inventor： Eyyüb Hachmie SARI ,  Vanessa COURVILLE ,  Mohan LIU ,  Vahid PARTOVI NIA

IPC: G06F17/12 ,  G06F7/50 ,  G06F7/523 ,  G06F7/544

CPC classification number: G06F17/12 ,  G06F7/50 ,  G06F7/523 ,  G06F7/5443

Abstract: Methods and systems for generating an integer neural network are described. The method includes receiving an input vector comprising a plurality of input values. The plurality of input values are represented using a desired number bits. The input vector is multiplied by a weight vector, and the products of which are summed to obtain a first value. The first value is quantized and applied to a piecewise linear activation function to obtain a second value. The piecewise linear activation function is a set of linear function that collectively approximate a nonlinear activation function. The second value is quantized to generate the output of the neuron in the integer neural network.