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.

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: In one embodiment, a trainable logic includes determination logic configured to determine a plurality of available receiver configurations and associate each receiver configuration with a context matrix; codebook logic configured to select a quantisation codebook to be used by the trainable logic for the context matrices; and learning logic configured to learn from a training dataset including a plurality of received signal samples relevant to reconstruction of a transmitted message. The learning logic is configured to generate, from the training dataset, a set of superposed parameters and context matrices corresponding to the plurality of available receiver configurations and a set of contextual parameters for each context; quantize the context matrices according to the quantisation codebook; and repeat the generation of superposed parameters, context matrices and quantization of context matrices until a stop criterion is met.

Abstract: Disclosed are apparatuses, systems, and techniques that may use machine learning for determining transmitted signals in communication systems that deploy orthogonal frequency division multiplexing. A system for performing the disclosed techniques includes receiving (RX) antennas to receive RX signals, each RX signal received over a respective resource element of a resource grid. Individual resource elements of the resource grid are associated with different radio subcarriers and/or data symbols. The RX signals include a combination of a plurality of transmitted (TX) streams. The system further includes a processing device to process the RX signals using one or more neural network models to determine TX data symbols transmitted via the plurality of TX streams.

Abstract: To obtain delay spread estimations and/or Doppler spread estimations, data representing received data is input to at least one trained model, the trained model outputting spread estimations.

Abstract: A method comprising receiving a modulated radio signal transmitting coded information bits, performing demodulating on the modulated radio signal, wherein demodulating comprises performing orthogonal time frequency space demodulation, performing equalization on the demodulated radio signal to obtain equalized symbols, obtaining log-likelihood ratios for the coded information bits from the equalized symbols using a trained machine learning model, and reconstructing the coded information bits.

Abstract: An apparatus for optimization of signal shaping for a multi user multiple input multiple output, MU-MIMO, communication system, including circuitry configured for receiving a bit vector; and for determining a constellation vector, wherein the circuitry for determining the constellation vector includes a Geometric Shaping and Labeling Block, GSLB, for modulating the bit vector, wherein the GSLB is configured to implement an algorithm with one or more trainable parameters.

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: Neural network-based structures for action user equipment device detection, estimation of time-of-arrival, and estimation of carrier frequency offset utilized with the narrowband physical random-access channel of wireless communication systems. The structure includes a neural network to generate predictions of active user equipment devices, and a twin neural network to generate time-of-arrival predictions for signals from the user equipment devices and carrier frequency offset predictions for signals from the user equipment devices.

Abstract: An apparatus, method and computer program performs initializing parameters of a transmission system. The transmission system comprises a transmitter, a first channel, a relay, a second channel and a receiver. The transmitter includes a transmitter algorithm having trainable weights, the relay includes a relay algorithm having trainable weights and the receiver includes a receiver algorithm having trainable weights. A first training sequence of messages is received, and the first training sequence of messages is sent from the transmitter to the relay using the first channel and is sent from the relay to the receiver using the second channel. A loss function is obtained or generated, and trainable parameters of the transmission system are updated based on the loss function. The trainable parameters include some of the trainable weights of the transmitter, some of the trainable weights of the relay, and some of the trainable weights of the receiver.

Abstract: A communication system including at least one receiver and at least one transmitter is described. The receiver is configured to communicate with the transmitter using a plurality of resource elements within a time-frequency OFDM grid. The transmitter is configured to transmit data-carrying symbols using all resource elements of the plurality of resource elements within the OFDM grid, wherein the data-carrying symbols are modulated using a constellation C. The receiver is configured to receive the data-carrying symbols on all resource elements of the plurality of resource elements within the OFDM grid, and to implement a neural network, configured to operate jointly on the plurality of resource elements, and to output, based on the received data-carrying symbols, a plurality of LLRs to reconstruct information bits from the received data-carrying symbols. The neural network is optimized with respect to the constellation C.

Abstract: An apparatus, method and computer program is described comprising: initialising trainable parameters of a transmission system having a transmitter, a channel and a receiver; generating training symbols on the basis of a differentiable distribution function; 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; and generating updated parameters of the transmission system in order to minimise the loss function.

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.

Abstract: An apparatus, method and computer program is described including: receiving, at a receiver of a transmissions system, transmitted signals from each of a plurality of transmitters, wherein each transmitter communicates with the receiver over one of a plurality of channels 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 the weights of the transmitter algorithm, at the receiver, based on a loss function; providing the updated weights to each transmitter of the transmission system; and repeating the receiving and updating until a first condition is reached.

Abstract: An apparatus, method and computer program product is disclosed. The apparatus may comprise means for receiving a performance metric for an antenna array comprised of a plurality of radiating elements, the performance metric being based on performance data associated with the antenna array, the antenna array having a radiating configuration represented by configuration parameters. The apparatus may also comprise means for updating the configuration parameters dependent on the received performance metric by means of estimating new configuration parameters for moving the performance metric towards a target value. The apparatus may also comprise means for re-configuring the radiating configuration of the antenna array based on the updated configuration parameters such that the physical geometry of the antenna array is changed.

Abstract: A communications system and method is described comprising: handshaking between a transmitter and a receiver of the communication system to initiate a training procedure, wherein said handshaking comprises a training setup request message comprising parameters for the training procedure, wherein the transmitter comprises trainable parameters and/or the receiver comprises trainable parameters; receiving identified training data from the transmitter at the receiver, wherein the training data comprises transmitter training data and/or receiver training data; sending training information from the receiver to the transmitter, wherein the training information comprises information for controlling training at the transmitter and/or the receiver; and terminating the training procedure.

Abstract: To provide demapping at a receiving side, a trained model for a demapper is used to output log-likelihood ratios of received signals representing data in a multi-user transmission. Inputs for the trained model for the demapper comprise a resource grid of equalized received signals.

Abstract: The present subject matter relates to a receiver including a detector for receiving a signal from a transmitter. The detector includes a set of one or more settable parameters, and circuitry configured for implementing an algorithm having trainable parameters. The algorithm is configured to receive as input information indicative of a status of a communication channel between the transmitter and the receiver and to output values of the set of settable parameters of the detector. The detector is configured to receive a signal corresponding to a message sent by the transmitter and to provide an output indicative of the message based on the received signal and the output values of the set of settable parameters of the detector.

Abstract: Neural network performance is improved in terms of training speed and/or accuracy by encoding (mapping) inputs to the neural network into a higher dimensional space via a hash function. The input comprises coordinates used to identify a point within a d-dimensional space (e.g., 3D space). The point is quantized and a set of vertex coordinates corresponding to the point are input to a hash function. For example, for d=3, space may be partitioned into axis-aligned voxels of identical size and vertex coordinates of a voxel containing the point are input to the hash function to produce a set of encoded coordinates. The set of encoded coordinates is used to lookup D-dimensional feature vectors in a table of size T that have been learned. The learned feature vectors are filtered (e.g., linearly interpolated, etc.) based on the coordinates of the point to compute a feature vector corresponding to the point.

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.