公开(公告)号：US11625610B2

公开(公告)日：2023-04-11

申请号：US16738455

申请日：2020-01-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyukjoon Kwon ,  Shailesh Chaudhari ,  Kee-Bong Song

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/084

Abstract: A method and system for training a neural network are herein provided. According to one embodiment, a method includes generating a first labelled dataset corresponding to a first modulation scheme and a second labelled dataset corresponding to a second modulation scheme, determining a first gradient of a cost function between a first neural network layer and a second neural network layer based on back-propagation using the first labelled dataset and the second labelled dataset, and determining a second gradient of the cost function between the second neural network layer and a first set of nodes of a third neural network layer based on back-propagation using the first labelled dataset. The first set of nodes of the third neural network layer correspond to a first plurality of detector classes associated with the first modulation scheme.

公开(公告)号：US20220318598A1

公开(公告)日：2022-10-06

申请号：US17339752

申请日：2021-06-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shailesh Chaudhari ,  Hyukjoon Kwon ,  Kee-Bong Song

IPC: G06N3/04 ,  H04W24/08 ,  H04B7/0413 ,  H04B7/08 ,  H04L5/00 ,  G06F17/16 ,  G06N3/08

Abstract: A learning-based system and method for interference whitening method. In some embodiments, the method includes receiving a signal; extracting a first set of features from the signal; making a first selection, by a first neural network, based on the first set of features; and selecting a first covariance matrix, from a plurality of covariance matrices, based on the first selection.

公开(公告)号：US12136979B2

公开(公告)日：2024-11-05

申请号：US17988244

申请日：2022-11-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyukjoon Kwon ,  Shailesh Chaudhari ,  Dongwoon Bai

IPC: H04L1/02 ,  H04B7/06 ,  H04B7/08

Abstract: A method and an apparatus are provided in which a vector is generated from a covariance matrix of a received signal. The vector is input to a neural network to obtain an enhanced vector. The enhanced vector is converted into an enhanced matrix. Interference whitening is performed on the received signal using a whitening filter based on the enhanced matrix.

公开(公告)号：US11960952B2

公开(公告)日：2024-04-16

申请号：US17834845

申请日：2022-06-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shailesh Chaudhari ,  Hyukjoon Kwon ,  Kee-Bong Song ,  Dongwoon Bai

IPC: G06K19/06 ,  G06K19/07 ,  G06N3/08

CPC classification number: G06K19/0723 ,  G06N3/08

Abstract: A system and method for configuring an RF network based on machine learning. In some embodiments, the method includes: receiving, by a first neural network, a first state and a first state transition, the first state including: one or more identifiers for available active ports, and a set of available connections between two or more circuit elements, each of the circuit elements being one of: (1) a first circuit type, (2) a second circuit type that operatively connects a circuit element of the first circuit type to one of the available active ports, and (3) the available active ports; and generating, by the first neural network, a first estimated quality value, for the first state transition.