公开(公告)号：US20240046076A1

公开(公告)日：2024-02-08

申请号：US18489210

申请日：2023-10-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Van Minh NGUYEN

IPC: G06N3/0464

CPC classification number: G06N3/0464

Abstract: Various embodiments relate to convolutional neural networks (CNN). CNN may be provided with a convolution kernel configured with binary weights. The CNN may be trained with the convolution kernel to determine a set of binary weights for the convolution kernel. The set of binary weights may be used for inference of the CNN. Devices, methods, and computer programs are disclosed.

公开(公告)号：US20250068908A1

公开(公告)日：2025-02-27

申请号：US18944150

申请日：2024-11-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Van Minh NGUYEN ,  Louis LECONTE

IPC: G06N3/08

Abstract: A device for training a binary deep neural network, where the device includes a processor, is configured to: generate a training signal in dependence on an error between an output of a prototype version of the binary deep neural network and an expected output, the prototype version of the binary deep neural network having multiple binary weights each having a respective value; and in dependence on the training signal, output for each binary weight of the prototype version of the binary deep neural network a respective decision to invert or maintain the respective value of the respective binary weight. This may allow the device to train a deep neural network including binary parameters directly in the binary domain without the need for gradient processing methods.

公开(公告)号：US20200092067A1

公开(公告)日：2020-03-19

申请号：US16692780

申请日：2019-11-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Van Minh NGUYEN ,  Marco MASO ,  Merouane DEBBAH

IPC: H04L5/00 ,  H04B7/06 ,  H04W72/08

Abstract: The invention relates to a communication device comprising: a communication interface configured to transmit a pilot signal via a communication channel to a further communication device and to receive a plurality of data elements representing channel state information (CSI) from the further communication device, wherein the plurality of data elements are a subset of a set of data elements representing the full channel state information (CSI) being available at the further communication device; and a processing unit configured to generate the full channel state information (CSI) on the basis of the plurality of data elements by applying a fitting scheme to the plurality of data elements received from the further communication device.