US 11,750,436 B2
Learning in communication systems
Jakob Hoydis, Paris (FR); Faycal Ait Aoudia, Saint-Cloud (FR); and Maximilian Stark, Massy (FR)
Assigned to Nokia Technologies Oy, Espoo, FL (US)
Appl. No. 17/613,578
Filed by Nokia Technologies Oy, Espoo (FI)
PCT Filed May 30, 2019, PCT No. PCT/EP2019/064146
§ 371(c)(1), (2) Date Nov. 23, 2021,
PCT Pub. No. WO2020/239232, PCT Pub. Date Dec. 3, 2020.
Prior Publication US 2022/0247614 A1, Aug. 4, 2022
Int. Cl. H04L 27/34 (2006.01); H04L 25/02 (2006.01); H04L 25/03 (2006.01)
CPC H04L 27/3405 (2013.01) [H04L 25/0268 (2013.01); H04L 25/03165 (2013.01); H04L 2025/0377 (2013.01); H04L 2025/03598 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
at least one processor; and
at least one memory including computer program code, the at least one memory and the computer program configured, with the at least one processor, to cause the apparatus to perform at least:
initialising trainable parameters of a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm for converting one or more inputs into one or more data symbols and a modulator for converting said data symbols into transmit symbols in accordance with a modulation scheme, wherein the trainable parameters of the transmission system include a probability function defining a probability that individual data symbols are output by the transmitter algorithm;
generating training symbols on the basis of a distribution function, wherein the distribution function is differentiable;
transmitting modulated training symbols to the receiver over the channel in a training mode;
generating a loss function based on the generated training symbols and the modulated training symbols as received at the receiver of the transmission system;
generating updated parameters of the transmission system in order to minimise the loss function, wherein generating updated parameters of the transmission system comprise updating the parameters of the transmitter algorithm; and
repeating the generating the training symbols, generating the loss function and updating parameters of the transmission system until a first condition is reached.