公开(公告)号：US20210192320A1

公开(公告)日：2021-06-24

申请号：US16757560

申请日：2017-10-23

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Jakob HOYDIS

IPC: G06N3/04 ,  G06N3/063 ,  G06K9/62 ,  H04L25/03 ,  H04L25/497 ,  H04L5/00

Abstract: This specification relates to end-to-end learning in communication systems and describes: organising a plurality of transmitter neutral networks and a plurality of receiver neural networks into a plurality of transmitter-receiver neural network pairs, wherein a transmitter-receiver neural network pair is defined for each of a plurality of subcarrier frequency bands of a multi-carrier transmission system; arranging a plurality of symbols of the multi-carrier transmission system into a plurality of transmit blocks; mapping each of said transmit blocks to one of the transmitter-receiver neural network pairs; transmitting each symbol using the mapped transmitter-receiver neural network pair; and training at least some weights of the transmit and receive neural networks using a loss function for each transmitter-receiver neural network pair.

公开(公告)号：US20200252892A1

公开(公告)日：2020-08-06

申请号：US16778116

申请日：2020-01-31

Applicant: Nokia Technologies Oy

Inventor： Faycal AIT AOUDIA ,  Jakob HOYDIS

IPC: H04W56/00 ,  H04W72/04 ,  G06N3/04 ,  G06N3/08

Abstract: A method, apparatus, receiver and system provide timing synchronization during data transmission over a channel. In the context of a method, the method receives, for individual ones of a plurality of sequences of samples generated by a channel in response to transmission of corresponding frames that are comprised of a plurality of symbols including a preamble and one or more data symbols: (i) a probability vector and (ii) an indication of the sample of the respective sequence that corresponds to the particular symbol of the corresponding frame. The method determines one or more updated parameters of a frame detector of a receiver that receives the sequence of samples from the channel. The method determines one or more updated parameters of a preamble generator of a transmitter that provides the preamble for transmission over the channel.

公开(公告)号：US20240314003A1

公开(公告)日：2024-09-19

申请号：US18573567

申请日：2021-06-28

Applicant: Nokia Technologies Oy

Inventor： Faycal AIT AOUDIA ,  Jakob HOYDIS

IPC: H04L25/03

CPC classification number: H04L25/03834 ,  H04L25/03165

Abstract: In a communication system, a transmitter includes a transmit filter for pulse shaping to produce a transmit signal subject to a signal constraint for transmission over a channel to a receiver, and the receiver includes a receive filter to process a received signal. The transmit and receive filters are implemented through a filtering function with trainable parameters, the parameters obtained by joint optimization of the transmit and receive filters to maximize the transmission rate for the channel model and the signal constraint. The learning method for obtaining the parameters includes: simulating the channel response depending on the transmit and receive filters, simulating a channel noise correlation depending on the receive filter, computing channel outputs for random samples by applying the simulated channel response and a random noise correlated to reflect the simulated channel noise correlation, learning the parameters by minimizing a loss function subject to at least one signal constraint.

公开(公告)号：US20240146362A1

公开(公告)日：2024-05-02

申请号：US17964679

申请日：2022-10-12

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Faycal AIT AOUDIA ,  Jakob HOYDIS ,  Stefan WESEMANN

IPC: H04B7/0456 ,  H04B7/06

CPC classification number: H04B7/0456 ,  H04B7/0615

Abstract: An apparatus, method and computer program is described comprising: transmitting signals from a transmitter of a multiple-input single-output transmission system to a receiver of the transmission system, wherein the transmitter communicates with the receiver over a plurality of channels of the transmission system, wherein the transmitter includes a transmitter algorithm having at least some trainable weights, wherein said transmitter algorithm converts a sequence of coded bits into time domain baseband symbols for transmission over said channels; updating weights of said transmitter algorithm based on a loss function, said loss function having a first loss term, a second loss term and a variable defining a weighting of those loss terms, wherein the first parameter relates to an information rate of communications from the transmitter to the receiver; and repeating the transmitting and updating until a first condition is reached.

公开(公告)号：US20230199705A1

公开(公告)日：2023-06-22

申请号：US17924947

申请日：2021-05-07

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Pavan KOTESHWAR SRINATH ,  Jakob HOYDIS

IPC: H04W64/00 ,  H04W24/02 ,  H04B7/06

CPC classification number: H04W64/006 ,  H04W24/02 ,  H04B7/0626 ,  G06N3/02

Abstract: According to the present disclosure, a first dataset comprising CSI measurements associated with first UEs and actual positions of the first UEs within a coverage region of a network node is received. Then, a second dataset comprising at least one CSI measurement associated with at least one second UE whose position within the coverage region of the network node is to be estimated is received. After that, based on the first and second datasets, the at least one CSI measurement associated with the at least one second UE is assigned to one of the first UEs that appears closest to the at least one second UE. Finally, the position of the at least one second UE within the coverage region of the network node is estimated by using a semi-supervised machine learning algorithm that receives the first and second datasets and the actual position of the closest first UE.

公开(公告)号：US20220393795A1

公开(公告)日：2022-12-08

申请号：US17771261

申请日：2019-10-31

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Mathieu GOUTAY ,  Faycal AIT AOUDIA ,  Jakob HOYDIS

IPC: H04L1/16

Abstract: A retransmission method in a communication system, wherein the communication system comprises at least one transmitter and at least one receiver with a communication channel between the transmitter and the receiver, the method comprising: utilising in the transmitter a transmitter algorithm with trainable weights and in the receiver a receiver algorithm with trainable weights; generating (302) by the transmitter symbols to be transmitted based on a message to be sent and feedback received from the receiver and transmitting the symbols; generating (304) by the receiver a predicted message based on the received symbols, evaluating (306) the predicted message based on a criterion and providing (312), utilising an algorithm with trainable weights, feedback symbols as a response to the transmitter if the evaluation indicates the predicted message is not acceptable.

公开(公告)号：US20220263596A1

公开(公告)日：2022-08-18

申请号：US17621747

申请日：2019-06-27

Applicant: Nokia Technologies Oy

Inventor： Faycal AIT AOUDIA ,  Maximilian STARK ,  Jakob HOYDIS

IPC: H04L1/00 ,  H04L25/49 ,  G06N3/04 ,  G06N3/08

Abstract: An apparatus, method and computer program is described including circuitry configured for using a transmitter algorithm to convert one or more inputs at a transmitter of a transmission system into one or more data symbols, wherein: the transmission system includes the transmitter implementing said transmitter algorithm, a channel and a receiver including a receiver algorithm; the transmitter algorithm includes trainable parameters for converting one or more received data symbols into one or more outputs; and the transmitter algorithm is stochastic.

公开(公告)号：US20220191079A1

公开(公告)日：2022-06-16

申请号：US17541522

申请日：2021-12-03

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Jakob HOYDIS ,  Vahid AREF ,  Ahmed ELKELESH ,  Sebastian CAMMERER

IPC: H04L27/26 ,  H04L5/00 ,  H04L1/20

Abstract: Different solutions for an apparatus comprising a predictor predicting decodability of received symbols are disclosed. Decoding is performed based on the prediction.

公开(公告)号：US20220094462A1

公开(公告)日：2022-03-24

申请号：US17482610

申请日：2021-09-23

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Faycal AIT AOUDIA ,  Jakob HOYDIS

IPC: H04L1/00 ,  H04L1/20 ,  H04W72/08

Abstract: This specification describes an apparatus relating to rate adaptation. The apparatus may comprise a processor and a memory including instructions, the instructions, when executed by the processor, cause the apparatus to provide first data representing an estimate of a communications link based on a signal received over said communications link from a transmitter. The apparatus may determine an estimated achievable data rate over said communications link for each of a plurality of link configurations which have respective combinations of modulation scheme and pilot symbol pattern which correspond to one or more transmitter link configurations, the estimated achievable data rate for a particular link configuration being determined based on the first data, and the modulation scheme and the pilot pattern of the particular reference link configuration. The apparatus may select a transmitter link configuration based on the estimated achievable data rates.

公开(公告)号：US20210219099A1

公开(公告)日：2021-07-15

申请号：US17145955

申请日：2021-01-11

Applicant: Nokia Technologies Oy

Inventor： Pavan KOTESHWAR SRINATH ,  Jakob HOYDIS

IPC: H04W4/029 ,  G01S5/02

Abstract: An apparatus, method and computer program is described comprising: generating a first loss function component comprising comparing first location data with first location estimates, wherein the first location estimates are based on channel state data, wherein the first location estimates are generated using a model, and wherein the model comprises a plurality of trainable parameters; generating a second loss function component comprising comparing the first location data with second location estimates, wherein the second location estimates are based on channel state data that have been subjected to a first augmentation and wherein the second location estimates are generated using the model; generating a third loss function component comprising comparing third location estimates based on channel state data and fourth location estimates based on channel state data that have been subjected to a second augmentation, wherein the third and fourth location estimates are generated using the model; and training the trainable parameters of the model by minimising a loss function based on a combination of the first, second and third loss function components.