公开(公告)号：US20230089380A1

公开(公告)日：2023-03-23

申请号：US17993430

申请日：2022-11-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chenhan JIANG ,  Hang XU ,  Zhenguo LI ,  Xiaodan LIANG

IPC: G06N3/04

Abstract: A neural network construction method and apparatus in the field of artificial intelligence, to accurately and efficiently construct a target neural network. The constructed target neural network has high output accuracy, may be further applied to different application scenarios, and has a strong generalization capability. The method includes: obtaining a start point network, where the start point network includes a plurality of serial subnets; performing at least one time of transformation on the start point network based on a preset first search space to obtain a serial network, where the first search space includes a range of parameters used for transforming the start point network; and if the serial network meets a preset condition, training the serial network by using a preset dataset to obtain a trained serial network; and if the trained serial network meets a termination condition, obtaining a target neural network based on the trained serial network.

公开(公告)号：US20230087526A1

公开(公告)日：2023-03-23

申请号：US17993507

申请日：2022-11-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Weiran HUANG ,  Zhenguo LI ,  Aoxue LI ,  Liwei WANG

IPC: G06V10/774 ,  G06V10/82

Abstract: A neural network training method, an image classification system, and a related device, which may be applied to the artificial intelligence field. Feature extraction is performed on images in a training set (including a first set and a second set) by using a prototype network, to obtain first feature points, in a feature space, of a plurality of images in the first set and second feature points of a plurality of images in the second set. The first feature points are used for calculating a prototype of a class of an image, and the second feature points are used for updating a network parameter of the prototype network. A semantic similarity between classes of the images in the second set is obtained, to calculate a margin value between the classes of the images. Then, a loss function is adjusted based on the margin value.

公开(公告)号：US20220261591A1

公开(公告)日：2022-08-18

申请号：US17661448

申请日：2022-04-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Ruiming TANG ,  Huifeng GUO ,  Zhenguo LI ,  Xiuqiang HE

IPC: G06K9/62

Abstract: The method includes: obtaining a plurality of pieces of feature data; automatically performing two different types of nonlinear combination processing operations on the plurality of pieces of feature data to obtain two groups of processed data, where the two groups of processed data include a group of higher-order data and a group of lower-order data, the higher-order data is related to a nonlinear combination of m pieces of feature data in the plurality of pieces of feature data, and the lower-order data is related to a nonlinear combination of n pieces of feature data in the plurality of pieces of feature data, where m≥3, and m>n≥2; and determining prediction data based on a plurality of pieces of target data, where the plurality of pieces of target data include the two groups of processed data.

公开(公告)号：US20190149438A1

公开(公告)日：2019-05-16

申请号：US16245717

申请日：2019-01-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhenguo LI ,  Ge LUO ,  Ke YI

IPC: H04L12/26

Abstract: A data processing method, includes receiving a data flow; generating a triplet set according to the data flow, where each triplet in the set includes three items, the first item is a first element in the data flow, the second item includes a first time point at which the first element appears in the data flow and a first quantity of times that corresponds to the first time point, and the third item includes a second time point at which the first element appears in the data flow and a second quantity of times that corresponds to the second time point; and performing data processing on the data flow according to the triplet set. In the embodiments of the present application, the triplet set may be generated based on the data flow.

公开(公告)号：US20250104406A1

公开(公告)日：2025-03-27

申请号：US18975854

申请日：2024-12-10

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Fengwei ZHOU ,  Chuanlong XIE ,  Qishi DONG ,  Tianyang HU ,  Yongxin YANG ,  Zhenguo LI

IPC: G06V10/776 ,  G06V10/70 ,  G06V10/77 ,  G06V10/774

Abstract: This application relates to a model migration method in the field of artificial intelligence, including: obtaining sample data of a target task, where the sample data includes a plurality of image samples; separately evaluating N pre-trained models based on the sample data, to obtain N evaluation values, where the evaluation value represents adaptation between the pre-trained model and the target task, and N≥2; determining K pre-trained models from the N pre-trained models based on the N evaluation values, where the K pre-trained models are models corresponding to first K evaluation values obtained by sorting the N evaluation values in descending order, and 1≤K≤N; and processing the sample data based on the K pre-trained models to obtain a target model used to process the target task, where the target model includes the K pre-trained models.

公开(公告)号：US20240235577A1

公开(公告)日：2024-07-11

申请号：US18618306

申请日：2024-03-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shifeng ZHANG ,  Ning KANG ,  Tom RYDER ,  Zhenguo LI

IPC: H03M7/30 ,  G06F7/50 ,  G06F7/523 ,  G06F7/72

CPC classification number: H03M7/6011 ,  G06F7/50 ,  G06F7/523 ,  G06F7/72 ,  H03M7/6005

Abstract: This application relates to the field of artificial intelligence, and discloses a data encoding method, a data decoding method, and data processing apparatuses. Both the data encoding method and the data decoding method relate to an invertible flow-based model. The invertible flow-based model includes a target invertible flow layer, a model parameter of the target invertible flow layer is used to constrain an auxiliary variable generated in an inverse transform processing process, an operation corresponding to the target invertible flow layer includes a multiplication operation and a division operation that are determined based on the model parameter, and the auxiliary variable is an increment of a product of the multiplication operation or a remainder generated through the division operation.

公开(公告)号：US20240152770A1

公开(公告)日：2024-05-09

申请号：US18411616

申请日：2024-01-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hang XU ,  Xiaozhe REN ,  Yichun YIN ,  Li QIAN ,  Zhenguo LI ,  Xin JIANG ,  Jiahui GAO

IPC: G06N3/0985 ,  G06N3/04

CPC classification number: G06N3/0985 ,  G06N3/04

Abstract: This application relates to the artificial intelligence field, and discloses a neural network search method and a related apparatus. The neural network search method includes: constructing attention heads in transformer layers by sampling a plurality of candidate operators during model search, to construct a plurality of candidate neural networks, and comparing performance of the plurality of candidate neural networks to select a target neural network with higher performance. In this application, a transformer model is constructed with reference to model search, so that a new attention structure with better performance than an original self-attention mechanism can be generated, and effect in a wide range of downstream tasks is significantly improved.

公开(公告)号：US20240070436A1

公开(公告)日：2024-02-29

申请号：US17900592

申请日：2022-08-31

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hang XU ,  Lu HOU ,  Guansong LU ,  Minzhe NIU ,  Zhenguo LI ,  Runhui HUANG ,  Lewei YAO ,  Chunjing XU ,  Xiaodan LIANG

IPC: G06N3/04 ,  G06F40/284

CPC classification number: G06N3/0454 ,  G06F40/284

Abstract: A method is provided for data processing performed by a processing system. The method comprises determining a set of first tokens for first data and a set of second token for second data, each token comprising information associated with a segment of the respective data, determining pair-wise similarities between the set of first tokens and the set of second tokens, each pair comprising a first token in the set of first tokens and a second token in the set of second tokens, determining, for each first token in the set of first tokens, a maximum similarity based on the determined pair-wise similarities between the respective first token and the second tokens in the set of second tokens, and determining a first similarity between the first data and the second data by aggregating the maximum similarities corresponding to the first tokens in the set of first set of tokens.

公开(公告)号：US20230144209A1

公开(公告)日：2023-05-11

申请号：US18064016

申请日：2022-12-09

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xinyue CAI ,  Hang XU ,  Wei ZHANG ,  Zhen YANG ,  Zhenguo LI

IPC: G06V20/56 ,  G06T5/20 ,  G06T7/11 ,  G06V10/771 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V20/588 ,  G06T5/20 ,  G06T7/11 ,  G06V10/771 ,  G06V10/803 ,  G06V10/82 ,  G06T2207/30256

Abstract: This disclosure discloses lane line detection methods and devices. In an implementation, features extracted by different layers of the neural network are fused to obtain a fused second feature map, so that the second feature map obtained through fusion processing has a plurality of layers of features. The fused second feature map has a related feature of a low-layer receptive field and a related feature of a high-layer receptive field. Afterwards, an output predicted lane line set is divided into groups, where each predicted lane line in each group has an optimal prediction interval.

公开(公告)号：US20220292357A1

公开(公告)日：2022-09-15

申请号：US17826873

申请日：2022-05-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hang XU ,  Zewei CHEN ,  Zhenguo LI

IPC: G06N3/08

Abstract: A neural network search method, apparatus, and device are provided, and relate to the field of artificial intelligence technologies, and specifically, to the field of automatic machine learning technologies. The method includes: A computing device obtains a dataset and N neural networks (S602), where N is a positive integer; and performs K evolutions on the N neural networks to obtain neural network obtained through the Kth evolution, where K is a positive integer (S604). In a process of each evolution, a network structure of a neural network obtained in previous evolution is mutated; and a candidate neural network is selected, based on a partially ordered hypothesis, from networks obtained through mutation.