-
1.发明公开公开(公告)号：US20240104346A1
公开(公告)日：2024-03-28
申请号：US17945978
申请日：2022-09-15
Applicant: Huawei Technologies Co., Ltd.
Inventor： Lu HOU , Chaofan TAO , Wei ZHANG , Lifeng SHANG , Xin JIANG , Qun LIU , Li QIAN
IPC: G06N3/04
CPC classification number: G06N3/0454
Abstract: A method is provided for quantizing a neural network model performed by a processing system. The method comprises determining a scaling factor based on a distribution of weights associated with the neural network model, determining quantized weights based on the scaling factor and the weights associated with the distribution, determining a training loss of the neural network model based on the quantized weights during training of the neural network model, and determining an updated scaling factor for the neural network model based on a gradient of the training loss.
-
公开(公告)号：US20230048031A1
公开(公告)日：2023-02-16
申请号：US17964165
申请日：2022-10-12
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
IPC: G06N3/08 , G06F40/279 , G06F40/103
Abstract: Relating to the field of artificial intelligence, and specifically relating to the field of natural language processing, a data processing method includes and an apparatus performs: determining original text samples, where masking processing is not performed on the original text samples; and performing mask processing on the original text samples to obtain mask training samples, where the mask processing makes mask proportions of the mask training samples unfixed, and the mask training samples each are used to train a pretrained language model PLM. Training the PLM by using the mask training samples whose mask proportions are unfixed can enhance mode diversity of the training samples of the PLM. Therefore, features learned by the PLM are also diversified, a generalization capability of the PLM can be improved, and a natural language understanding capability of the PLM obtained through training can be improved.
-
公开(公告)号：US20240046067A1
公开(公告)日：2024-02-08
申请号：US18380581
申请日：2023-10-16
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Junqiu WEI , Yi LIAO , Xin JIANG , Qun LIU , Li QIAN
IPC: G06N3/04
CPC classification number: G06N3/04
Abstract: A data processing method includes: obtaining a first embedding vector for indicating a known data unit and a position of the known data unit and a second embedding vector for indicating a position of a to-be-predicted data unit; processing the first embedding vector by using a target encoder, to obtain an output vector; and processing the output vector and the second embedding vector by using a target prediction network, to obtain a to-be-predicted data unit. According to the method, M pieces of additional position information do not need to be separately set as input of the target encoder, and a quantity of latent variables of intermediate output of the target encoder is also consistent with a quantity of input embedding vectors, thereby reducing a computation amount and memory consumption of the target encoder.
-
公开(公告)号：US20220383078A1
公开(公告)日：2022-12-01
申请号：US17882895
申请日：2022-08-08
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Lu HOU , Lifeng SHANG , Xin JIANG
Abstract: In a data processing method, a processing device obtains a first neural network model and an available resource state of a terminal device, and determines a second neural network model based on the first neural network model and the available resource state. An appropriate model size is determined based on the available resource state, and a part of the first neural network model is selected, based on the determined model size, as the second neural network model on which data processing is to be performed.
-
公开(公告)号：US20240119268A1
公开(公告)日：2024-04-11
申请号：US18524523
申请日：2023-11-30
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Lu HOU , Lifeng SHANG , Xin JIANG , Li QIAN
IPC: G06N3/048
CPC classification number: G06N3/048
Abstract: This disclosure relates to the field of artificial intelligence, and discloses a data processing method. The method includes: obtaining a transformer model including a target network layer and a target module; and processing to-be-processed data by using the transformer model, to obtain a data processing result. The target module is configured to: perform a target operation on a feature map output at the target network layer, to obtain an operation result, and fuse the operation result and the feature map output, to obtain an updated feature map output. In this disclosure, the target module is inserted into the transformer model, and the operation result generated by the target module and an input are fused, so that information carried in a feature map output by the target network layer of the transformer model is increased.
-
Patent Agency Ranking
公开(公告)号：US20230177410A1
公开(公告)日：2023-06-08
申请号：US18161620
申请日：2023-01-30
Applicant: Huawei Technologies Co., Ltd.
Abstract: A model training method applied to the field of artificial intelligence is disclosed. The method includes: sending a first submodel to a first device, where the first submodel is obtained by compressing a to-be-trained model; receiving a first gradient sent by the first device, where the first gradient is obtained when the first device trains the first submodel; and performing model training on the to-be-trained model based on at least the first gradient, to obtain an updated to-be-trained model. In the method, a server compresses the to-be-trained model and delivers the to-be-trained model to a terminal device, so that the terminal device does not need to train a large model with a same scale as that of the server.
-
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：US20210166693A1
公开(公告)日：2021-06-03
申请号：US17171166
申请日：2021-02-09
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Yingtao LI , Xin JIANG , Xiao CHEN , Baofeng ZHANG , Li QIAN
Abstract: The application relates to the field of man-machine interaction in artificial intelligence and provides a multi-task processing method. The method includes the following operations: determining a first task based on request information entered by a user; obtaining key information corresponding to the first task and executing the first task, where the key information includes one or more slots and values of the one or more slots; storing task status information of the first task, where the task status information includes the key information; and predicting and initiating a second task based on the task status information of the first task. A man-machine interaction system may predict a next task based on the stored task status information, and actively initiate the predicted task. This improves intelligence and efficiency of multi-task processing by the man-machine interaction system.
-
公开(公告)号：US20190205348A1
公开(公告)日：2019-07-04
申请号：US16292992
申请日：2019-03-05
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
IPC: G06F16/9532 , G06F16/9032 , G06F17/18 , G06F16/9538
CPC classification number: G06F16/9532 , G06F16/90332 , G06F16/9538 , G06F17/18 , H04L29/06
Abstract: The present invention discloses a method and an apparatus for sending a search request. The method includes: during a running procedure of a search engine client, generating a forged search request, where the forged search request carries a forged search word; and sending the forged search request to the search engine server. The forged search request is sent to the search engine server, to serve as a factor interfering with an analysis of a user behavior by the search engine server based on a true search request, to prevent the search engine server from analyzing the user behavior based on a search word entered by a user, thereby improving user experience. It is avoided that, in the prior art, a search engine server analyzes a user behavior based on a search word entered by a user.
-
公开(公告)号：US20240220730A1
公开(公告)日：2024-07-04
申请号：US18604138
申请日：2024-03-13
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Xiaojun MENG , Yasheng WANG , Xin JIANG , Qun LIU
IPC: G06F40/30
CPC classification number: G06F40/30
Abstract: A text data processing method, a neural-network training method, and related devices are provided. The methods may be applied to the text data processing field in the artificial intelligence field. The method includes: obtaining a to-be-processed text, where the to-be-processed text includes a plurality of characters; and processing the to-be-processed text by using a target model to obtain a prediction result, where the prediction result indicates to split the to-be-processed text into a plurality of target character sets, the prediction result further includes a plurality of first labels, one first label indicates semantics of one target character set, and the plurality of first labels are used to determine an intention of the to-be-processed text.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.016 seconds)
