公开(公告)号：US11444736B2

公开(公告)日：2022-09-13

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 ,  H04B7/0417

Abstract: The application relates to a communication device comprising: a communication interface configured to transmit a pilot signal via a communication channel to a second communication device and to receive a plurality of data elements representing channel state information (CSI) from the second 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 second 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 second communication device.

公开(公告)号：US20220237456A1

公开(公告)日：2022-07-28

申请号：US17659543

申请日：2022-04-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jean-Claude Belfiore ,  Georgios Paschos ,  Dimitrios Tsilimantos ,  Apostolos Destounis ,  Spyridon Vassilaras ,  Marina Costantini ,  Nikolaos Liakopoulos ,  Van Minh Nguyen ,  Merouane Debbah

IPC: G06N3/08 ,  H03M13/13 ,  H03M13/00

Abstract: A data processing system having a neural network architecture for receiving a binary network input and, in dependence on the binary network input, propagating signals via a plurality of processing nodes, in accordance with respective binary weights, to form a network output, the data processing system being configured to train a node by implementing an error correcting function to identify a set of binary weights which minimize, for a given input to the node, any error between an output of the node when formed in accordance with current binary weights of the node and a preferred output from the node and to update the binary weights of the node to be the identified weights. This training is performed without storing and/or using any higher arithmetic precision weights or other components.