公开(公告)号：US20220215227A1

公开(公告)日：2022-07-07

申请号：US17704551

申请日：2022-03-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guilin LI ,  Zhenguo LI ,  Xing ZHANG

IPC: G06N3/04 ,  G06N3/063

Abstract: This application provides a neural architecture search method, an image processing method and apparatus, and a storage medium. The method includes: determining a search space and a plurality of structuring elements, stacking the plurality of structuring elements to obtain an initial neural architecture at a first stage, and optimizing the initial neural architecture at the first stage to be convergent; and after an initial neural architecture optimized at the first stage is obtained, optimizing the initial neural architecture at a second stage to be convergent, to obtain optimized structuring elements, and building a target neural network based on the optimized structuring elements. Each edge of the initial neural architecture at the first stage and each edge of the initial neural architecture at the second stage correspond to a mixed operator including one type of operations and a mixed operator including a plurality of types of operations respectively.

公开(公告)号：US20230141145A1

公开(公告)日：2023-05-11

申请号：US18150748

申请日：2023-01-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Weijun HONG ,  Guilin LI ,  Weinan ZHANG ,  Yong YU ,  Xing ZHANG ,  Zhenguo LI

IPC: G06N3/04 ,  G06N3/082

CPC classification number: G06N3/04 ,  G06N3/082

Abstract: A neural network building method and apparatus are disclosed, and relate to the field of artificial intelligence. The method includes: initializing a search space and a plurality of building blocks, where the search space includes a plurality of operators, and the building block is a network structure obtained by connecting a plurality of nodes by using the operator; during training, in at least one training round, randomly discarding some operators, and updating the plurality of building blocks by using operators that are not discarded; and building a target neural network based on the plurality of updated building blocks. In the method, some operators are randomly discarded. This breaks association between operators, and overcomes a co-adaptation problem during training, to obtain a target neural network with better performance.

公开(公告)号：US20180322212A1

公开(公告)日：2018-11-08

申请号：US16038892

申请日：2018-07-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guilin LI

IPC: G06F17/30

CPC classification number: G06F17/30867 ,  G06F17/30 ,  G06F17/3053

Abstract: The present invention discloses a network resource recommendation method, including: determining a first interest model according to a user behavior record in a current time window; calculating a similarity between any two interest models in the first interest model, a second interest model, and a third interest model, where a time window corresponding to the second interest model is adjacent to the current time window, the third interest model is determined based on all user behavior records in a reference time window set, the reference time window set includes N time windows prior to the time window corresponding to the second interest model; determining a fourth interest model and a recommendation algorithm according to the calculated similarity between any two interest models; generating a network resource recommendation list according to the fourth interest model and the recommendation algorithm; and making a recommendation according to the network resource recommendation list.