The nonlinearity of power amplifiers (PAs) has been a severe constraint in performance of modern wireless transceivers. This problem is even more challenging for the fifth generation (5G) cellular system since 5G signals have extremely high peak to average power ratio. Nonlinear equalizers that exploit both deep neural networks (DNNs) and Volterra series models are provided to mitigate PA nonlinear distortions. The DNN equalizer architecture consists of multiple convolutional layers. The input features are designed according to the Volterra series model of nonlinear PAs. This enables the DNN equalizer to effectively mitigate nonlinear PA distortions while avoiding over-fitting under limited training data. The non-linear equalizers demonstrate superior performance over conventional nonlinear equalization approaches.

According to an example embodiment, a radio receiver includes at least one processor and at least one memory including computer program code. The at least one memory and the computer program code may be configured to, with the at least one processor, cause the radio receiver to: obtain a data array including a plurality of elements, wherein each element in the plurality of elements in the data array corresponds to a subcarrier in a plurality of subcarriers and to a timeslot in a time interval; obtain a reference signal array representing a reference signal configuration applied during the time interval; implement a neural network; input data into the neural network, wherein the data includes at least the data array and the reference signal array. A radio receiver, a method and a computer program product are disclosed.

A receiver for use in a data channel on an integrated circuit device includes a non-linear equalizer having as inputs digitized samples of signals on the data channel, decision circuitry configured to determine from outputs of the non-linear equalizer a respective value of each of the signals, and adaptation circuitry configured to adapt parameters of the non-linear equalizer based on respective ones of the value. The non-linear equalizer may be a neural network equalizer, such as a multi-layer perceptron neural network equalizer, or a reduced complexity multi-layer perceptron neural network equalizer. A method for detecting data on a data channel on an integrated circuit device includes performing non-linear equalization of digitized samples of input signals on the data channel, determining from output signals of the non-linear equalization a respective value of each of the output signals, and adapting parameters of the non-linear equalization based on respective ones of the value.

A device and a method for training a model are disclosed, wherein the method of training the model includes: first classifying a plurality of data packets using the model, wherein a first class is assigned to each data packet of a plurality of data packets, wherein the first class is associated with a receiver of a plurality of receivers; second classifying the plurality of data packets, wherein a second class is assigned to each data packet of the plurality of data packets, wherein the second class is associated with a receiver of the plurality of receivers; and training the model using the plurality of first classes and the plurality of second classes assigned to the plurality of data packets.

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.

An apparatus for processing a received radio signal includes at least one processor and at least one memory. The at least one memory storing computer program code. The at least one memory and the computer program code being configured to, with the at least one processor, cause the apparatus to at least in part perform processing (received radio signal data with first and second signal processing chains, which respectively include first and second processing modules configured to respectively determine first output and an estimation of the first output data, and determine second output data using a neural network based on the estimation; updating parameters of the neural network based on the first output data and the second output data; and after the updating, processing the received radio signal data with the second signal processing chain, without applying the first processing module.

An operating method of a wireless communication device performing an interference whitening operation includes obtaining first channel state information of the wireless communication device, selecting a selected mode from among a plurality of modes related to the interference whitening operation, the selected mode corresponding to the first channel state information, obtaining channel performance information according to the selected mode, and updating a value function expected value based on the first channel state information, the selected mode, and the channel performance information.

Methods and systems for generating an estimate of a bit error rate of a signal are provided. Methods and systems include obtaining an eye mask for a receiver, receiving a signal with the receiver, generating an eye mask probability density function of the eye mask, generating an eye diagram probability density function based on the signal, calculating a product of the eye mask probability density function and the eye diagram probability density function, summing the product of the eye mask probability density function and the eye diagram probability density function, and estimating the bit error rate of the signal based on the summing of the product of the eye mask probability density function and the eye diagram probability density function.

The technology relates to bandwidth constrained communication systems with neural network based detection. In some embodiments, a bandwidth constrained equalized transport (BCET) communication system comprises: a transmitter comprising an error control code encoder, a pulse-shaping filter, and a first interleaver; a communication channel; and a receiver comprising a neural network processing block that processes a received signal. The error control code encoder can append redundant information onto the signal. The pulse-shaping filter can intentionally introduce memory into the signal in the form of inter-symbol interference. The first interleaver can change a temporal order of the symbols in the signal. The error control code encoder can be a low-density parity-check (LDPC) error control code encoder. The neural network can be trained with positive mappings between transmitted and decoded training signals, or negative mappings between training signals and a null space of an LDPC generation matrix.

A machine learning (ML) agent operates at a transmitter to optimize signals transmitted across a communications channel. A physical signal modifier modifies a physical layer signal prior to transmission as a function of a set of signal modification parameters to produce a modified physical layer signal. The ML agent parses a feedback signal from a receiver across the communications channel, and determines a present tuning status as a function of the signal modification parameters and the feedback signal. The ML agent generates subsequent signal modification parameters based on the present tuning status and a set of stored tuning statuses, thereby updating the physical signal modifier to generate a subsequent modified physical layer signal to be transmitted across the communications channel.