公开(公告)号：US20240235626A1

公开(公告)日：2024-07-11

申请号：US18398982

申请日：2023-12-28

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Tugba Erpek

IPC: H04B7/0452 ,  G06N3/006 ,  G06N3/044 ,  G06N3/045 ,  G06N3/048 ,  G06N3/08 ,  G06N3/082 ,  G06N3/086 ,  G06N3/088 ,  H04B7/0413 ,  H04B7/06

CPC classification number: H04B7/0452 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  H04B7/0413 ,  G06N3/006 ,  G06N3/048 ,  G06N3/082 ,  G06N3/086 ,  H04B7/0626

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US11381286B2

公开(公告)日：2022-07-05

申请号：US17145501

申请日：2021-01-11

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Tugba Erpek

IPC: H04B7/02 ,  H04B7/0452 ,  G06N3/08 ,  H04B7/0413 ,  G06N3/04 ,  H04B7/06 ,  G06N3/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US10892806B2

公开(公告)日：2021-01-12

申请号：US16421694

申请日：2019-05-24

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Tugba Erpek

IPC: H04B7/04 ,  H04B7/0452 ,  G06N3/08 ,  H04B7/0413 ,  G06N3/04 ,  H04B7/06 ,  G06N3/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US11863258B2

公开(公告)日：2024-01-02

申请号：US17856611

申请日：2022-07-01

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Tugba Erpek

IPC: H04B7/04 ,  H04B7/0452 ,  G06N3/08 ,  H04B7/0413 ,  G06N3/088 ,  G06N3/044 ,  G06N3/045 ,  H04B7/06 ,  G06N3/086 ,  G06N3/006 ,  G06N3/082 ,  G06N3/048

CPC classification number: H04B7/0452 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  H04B7/0413 ,  G06N3/006 ,  G06N3/048 ,  G06N3/082 ,  G06N3/086 ,  H04B7/0626

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US20230089393A1

公开(公告)日：2023-03-23

申请号：US17856611

申请日：2022-07-01

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O`Shea ,  Tugba Erpek

IPC: H04B7/0452 ,  G06N3/08 ,  H04B7/0413 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US20210211164A1

公开(公告)日：2021-07-08

申请号：US17145501

申请日：2021-01-11

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O`Shea ,  Tugba Erpek

IPC: H04B7/0452 ,  G06N3/08 ,  H04B7/0413 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US10305553B2

公开(公告)日：2019-05-28

申请号：US16012691

申请日：2018-06-19

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O'Shea ,  Tugba Erpek

IPC: H04B7/0413 ,  H04B7/0452 ,  G06N3/08 ,  H04B7/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

公开(公告)号：US20180367192A1

公开(公告)日：2018-12-20

申请号：US16012691

申请日：2018-06-19

Applicant: Virginia Tech Intellectual Properties, Inc.

Inventor： Timothy James O`Shea ,  Tugba Erpek

IPC: H04B7/0452 ,  G06N3/08 ,  H04B7/06

CPC classification number: H04B7/0452 ,  G06N3/08 ,  H04B7/0626

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.