公开(公告)号：US20220327363A1

公开(公告)日：2022-10-13

申请号：US17848081

申请日：2022-06-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yixing Xu ,  Yehui Tang ,  Li Qian ,  Yunhe Wang ,  Chunjing Xu

IPC: G06N3/04 ,  G06N3/08

Abstract: A neural network training method in the artificial intelligence field includes: inputting training data into a neural network; determining a first input space of a second target layer in the neural network based on a first output space of a first target layer in the neural network; and inputting a feature vector in the first input space into the second target layer, where a capability of fitting random noise by the neural network when the feature vector in the first input space is input into the second target layer is lower than a capability of fitting the random noise by using an output space that is in the neural network and that exists when a feature vector in the first output space is input into the second target layer. This application helps avoid an overfitting phenomenon that occurs when the neural network processes an image, text, or speech.

公开(公告)号：US20240005164A1

公开(公告)日：2024-01-04

申请号：US18362435

申请日：2023-07-31

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yixing Xu ,  Kai Han ,  Yehui Tang ,  Yunhe Wang ,  Chunjing Xu

IPC: G06N3/084 ,  G06N3/04

CPC classification number: G06N3/084 ,  G06N3/04

Abstract: A neural network training method includes performing, in a forward propagation process, binarization processing on a target weight by using a binarization function, and using data obtained through the binarization processing as a weight of a first neural network layer in a neural network; and calculating, in a backward propagation process, a gradient of a loss function with respect to the target weight by using a gradient of a fitting function as a gradient of the binarization function.