A method for an end-to-end system for channel estimation includes obtaining data associated with a communication system. The communication system comprises a receiver, a transmitter, and a communication channel. A neural network is trained that models the communication channel of the communication system and this training is based on inputting the obtained data into the neural network and using a decoder. The neural network produces an output indicating a probability of a signal from the communication channel. The trained neural network is used for decoding information from the communication channel.

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. Non-linear 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.

Methods, systems, and devices for wireless communications are described. In some systems, a device, such as an internet of things (IoT) device, may include a configuration or software (e.g., in baseband) that is common for multiple applications of the device. In some aspects, the device may select a setting for at least some if not each of a set of parameters associated with or defining a device profile of the device based on an application of the device. The device may perform a mapping procedure to map the settings for the parameters associated with the device profile to one or more baseband configurations or baseband handles and the device may customize the baseband of the device using the one or more baseband configurations. As such, the device may operate or communicate using the baseband that is customized based on the device profile and application of the device.

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.

A BP detector of a wireless receiver apparatus reads a first parameter set or a second parameter set. The first parameter set includes a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique. The second parameter set includes a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique from a memory. The BP detector executes an iterative BP algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

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.

A BP detector of a wireless receiver apparatus reads a first parameter set or a second parameter set. The first parameter set includes a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique. The second parameter set includes a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique from a memory. The BP detector executes an iterative BP algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

An apparatus, method and computer program is described comprising receiving data at a receiver of a transmission system; using a receiver algorithm to convert data received at the receiver into an estimate of the first coded data, the receiver algorithm having one or more trainable parameters; generating an estimate of first data bits by decoding the estimate of the first coded data, said decoding making use of an error correction code of said encoding of the first data bits; generating a refined estimate of the first coded data by encoding the estimate of the first data bits; generating a loss function based on a function of the refined estimate of the first coded data and the estimate of the first coded data; updating the trainable parameters of the receiver algorithm in order to minimise the loss function; and controlling a repetition of updating the trainable parameters by generating, for each repetition, for the same received data, a further refined estimate of the first coded data, a further loss function and further updated trainable parameters.

A method, apparatus and computer program are described includes obtaining or generating a transmitter-training sequence of messages for a first transmitter of a first module of a transmission system, wherein the transmission system includes the first module having the first transmitter and a first receiver, a second module having a second transmitter and a second receiver, and a channel, wherein the first transmitter includes a transmitter algorithm having at least some trainable weights; transmitting a perturbed version of the transmitter-training sequence of messages from the first transmitter to the second receiver over the channel of the transmission system; receiving a first loss function at the first receiver from the second transmitter, wherein the first loss function is based on the transmitted perturbed versions of the transmitter-training sequence of messages as received at the second receiver and knowledge of the transmitter-training sequence of messages for the first transmitter of the transmission system; and training at least some weights of the transmitter algorithm of the first transmitter based on the first loss function.

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.