Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022002347 - TRAINING IN COMMUNICATION SYSTEMS

Publication Number WO/2022/002347
Publication Date 06.01.2022
International Application No. PCT/EP2020/068238
International Filing Date 29.06.2020
IPC
H04L 25/03 2006.1
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
25Baseband systems
02Details
03Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
G06N 3/02 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
CPC
G06K 9/627
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/088
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
088Non-supervised learning, e.g. competitive learning
H04L 25/03165
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
25Baseband systems
02Details
03Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
03006Arrangements for removing intersymbol interference
03165using neural networks
H04L 25/03343
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
25Baseband systems
02Details
03Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
03006Arrangements for removing intersymbol interference
03343Arrangements at the transmitter end
Applicants
  • NOKIA TECHNOLOGIES OY [FI]/[FI]
Inventors
  • AIT AOUDIA, Faycal
  • HOYDIS, Jakob
Agents
  • NOKIA EPO REPRESENTATIVES
Priority Data
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) TRAINING IN COMMUNICATION SYSTEMS
(FR) APPRENTISSAGE DANS DES SYSTÈMES DE COMMUNICATION
Abstract
(EN) An apparatus, method and computer program is described comprising: receiving, at a receiver (46) of a transmissions system (40), transmitted signals from each of a plurality of transmitters (42a, 42b, 42c), wherein each transmitter communicates with the receiver over one of a plurality of channels (44a, 44b, 44c) of the transmission system, wherein each transmitter includes a transmitter algorithm having at least some trainable weights, wherein each transmitter algorithm has the same trainable weights and wherein each of the transmitted signals is based on a perturbed channel symbol generated at the respective transmitter, wherein the channel symbols and perturbations are known to the receiver; updating said weights of said transmitter algorithm, at the receiver, based on a loss function; providing said updated weights to each transmitter of the transmission system; and repeating the receiving and updating until a first condition is reached.
(FR) Un appareil, un procédé et un programme informatique sont décrits, comprenant : la réception, au niveau d'un récepteur (46) d'un système de transmission (40), de signaux transmis à partir de chaque émetteur d'une pluralité d'émetteurs (42a, 42b, 42c), chaque émetteur communiquant avec le récepteur sur un canal parmi une pluralité de canaux (44a, 44b, 44c) du système de transmission, chaque émetteur comprenant un algorithme d'émetteur comprenant au moins certains poids capables d'apprentissage, chaque algorithme d'émetteur comprenant les mêmes poids d'apprentissage et chacun des signaux transmis étant basé sur un symbole de canal perturbé généré au niveau de l'émetteur respectif, les symboles de canal et les perturbations étant connus du récepteur ; la mise à jour desdits poids dudit algorithme d'émetteur, au niveau du récepteur, sur la base d'une fonction de perte ; la fourniture desdits poids mis à jour à chaque émetteur du système de transmission ; et la répétition de la réception et de la mise à jour jusqu'à ce qu'une première condition soit atteinte.
Latest bibliographic data on file with the International Bureau