公开(公告)号：US20230237309A1

公开(公告)日：2023-07-27

申请号：US18180841

申请日：2023-03-08

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiaoyun Zhou ,  Jiacheng Sun ,  Nanyang Ye ,  Xu Lan ,  Qijun Luo ,  Pedro Esperanca ,  Fabio Maria Carlucci ,  Zewei Chen ,  Zhenguo Li

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: A device for machine learning is provided, including a first neural network layer, a second neural network layer with a normalization layer arranged in between. The normalization layer is configured to, when the device is undergoing training on a batch of training samples, receive multiple outputs of the first neural network layer for a plurality of training samples of the batch, each output comprising multiple data values for different indices on a first dimension and a second dimension; group the outputs into multiple groups based on the indices on the first and second dimensions; form a normalization output for each group which are provided as input to the second neural network layer. According to the application, the training of a deep convolutional neural network with good performance that performs stably at different batch sizes and is generalizable to multiple vision tasks is achieved, thereby improving the performance of the training.

公开(公告)号：US20230111287A1

公开(公告)日：2023-04-13

申请号：US18065405

申请日：2022-12-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xu Lan ,  Sarah Parisot ,  Steven George McDonagh ,  Weiran Huang

IPC: G06N20/00 ,  G06V10/74 ,  G06V10/764 ,  G06V10/77

Abstract: A computer system and method are provided for training a machine learning system to perform a classification task by classifying input data into one of a plurality of classes. The system is configured to: receive per class training data from which per class representations can be derived, wherein each class is described by multiple representations; process the training data to form, for at least one class, a first proxy for a relatively global portion of an item of training data and multiple proxies for distinct relatively local portions of the item of training data, each proxy corresponding to a representation of the data belonging to that class.