公开(公告)号：US20250016247A1

公开(公告)日：2025-01-09

申请号：US18893780

申请日：2024-09-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Theodoros Giannakas ,  Dimitrios Tsilimantos ,  Apostolos Destounis

IPC: H04L67/59 ,  G06N3/098 ,  H04L67/00

Abstract: A device (400, 703) for processing a data sample (401, 701) to form a predicted output (409, 410) configured to: receive (801) the data sample (401, 701); input (802) the data sample (401, 701) and/or one or more of any intermediate outputs (406) derived from the data sample to a learnable control function (402); and in dependence on an output (403) of the function (402), perform (803) one of the following: (i) process the data sample (401, 701) to form the predicted output (409) using a first model (404, 405, 704) stored locally; and (ii) send the data sample (401, 701) and/or one or more of the any intermediate outputs (406) to a remote location (407, 702) for input to a second model (408, 705) stored remotely to form the predicted output (410).

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.