Systems and techniques are described that are directed to filter frequency response shift compensation, including compensating for shifting in the rejection band of the filter. Compensation for the shifting in the rejection band can include applying a pre-distortion to attenuate edge resource units (RUs), and applying PHY Protocol Data Unit (PPDU) scheduling schemes. For example, a PPDU scheduling scheme reduce bandwidth in the channel, thereby dropping the out of band RUs. Front ends provide feedback to a respective radio, which allows that radio to apply the appropriate pre-distortion. The front ends can include one or more filters enabling frequency domain coexistence between collocated radios operating in the differing Wi-Fi bands, and a coupler that provides the feedback indicating the frequency response shift to a radio. The radio can then apply a digital pre-distortion to compensate for the shifting in the rejection band.

This specification relates to end-to-end learning in communication systems and describes: organising a plurality of transmitter neutral networks and a plurality of receiver neural networks into a plurality of transmitter-receiver neural network pairs, wherein a transmitter-receiver neural network pair is defined for each of a plurality of subcarrier frequency bands of a multi-carrier transmission system; arranging a plurality of symbols of the multi-carrier transmission system into a plurality of transmit blocks; mapping each of said transmit blocks to one of the transmitter-receiver neural network pairs; transmitting each symbol using the mapped transmitter-receiver neural network pair; and training at least some weights of the transmit and receive neural networks using a loss function for each transmitter-receiver neural network pair.

This specification relates to end-to-end learning in communication systems and describes: organising a plurality of transmitter neutral networks and a plurality of receiver neural networks into a plurality of transmitter-receiver neural network pairs, wherein a transmitter-receiver neural network pair is defined for each of a plurality of subcarrier frequency bands of a multi-carrier transmission system; arranging a plurality of symbols of the multi-carrier transmission system into a plurality of transmit blocks; mapping each of said transmit blocks to one of the transmitter-receiver neural network pairs; transmitting each symbol using the mapped transmitter-receiver neural network pair; and training at least some weights of the transmit and receive neural networks using a loss function for each transmitter-receiver neural network pair.

A method for signal transmission using precoded symbol information involves estimating a two-dimensional model of a communication channel in a delay-Doppler domain. A perturbation vector is determined in a delay-time domain wherein the delay-time domain is related to the delay-Doppler domain by an FFT operation. User symbols are modified based upon the perturbation vector so as to produce perturbed user symbols. A set of Tomlinson-Harashima precoders corresponding to a set of fixed times in the delay-time domain may then be determined using a delay-time model of the communication channel. Precoded user symbols are generated by applying the Tomlinson-Harashima precoders to the perturbed user symbols. A modulated signal is then generated based upon the precoded user symbols and provided for transmission over the communication channel.

A signaling system is described. The signaling system comprises a transmit device, a receive device including a partial response receive circuit, and a signaling path coupling the transmit device and the receive device. The receive device observes an equalized signal from the signaling path, and includes circuitry to use feedback from the most recent previously resolved symbol to sample a currently incoming symbol. The transmit device equalizes transmit data to transmit the equalized signal, by applying weighting based on one or more data values not associated with the most recent previously resolved symbol value.

A signaling system is described. The signaling system comprises a transmit device, a receive device including a partial response receive circuit, and a signaling path coupling the transmit device and the receive device. The receive device observes an equalized signal from the signaling path, and includes circuitry to use feedback from the most recent previously resolved symbol to sample a currently incoming symbol. The transmit device equalizes transmit data to transmit the equalized signal, by applying weighting based on one or more data values not associated with the most recent previously resolved symbol value.

According to various examples, a communication system is described comprising a receiver configured to receive, for each of a plurality of object classes, via a wireless communication channel shared among transmitters of a respective set of transmitters, a superposition of transmitted hyperdimensional code words, comprising, for each transmitter of the respective set of transmitters, a hyperdimensional code word transmitted via the wireless communication channel and encoding data of an object of the object class acquired by the transmitter, a memory configured to store, for each of the plurality of object classes, the received superposition in association with the class, a processor configured to classify a hyperdimensional code word representing an object to be classified by correlating the hyperdimensional code word with each stored superposition and to generate a classification result corresponding to the object class associated with a superposition fulfilling a predetermined criterion based on correlation results.

According to various examples, a communication system is described comprising a receiver configured to receive, for each of a plurality of object classes, via a wireless communication channel shared among transmitters of a respective set of transmitters, a superposition of transmitted hyperdimensional code words, comprising, for each transmitter of the respective set of transmitters, a hyperdimensional code word transmitted via the wireless communication channel and encoding data of an object of the object class acquired by the transmitter, a memory configured to store, for each of the plurality of object classes, the received superposition in association with the class, a processor configured to classify a hyperdimensional code word representing an object to be classified by correlating the hyperdimensional code word with each stored superposition and to generate a classification result corresponding to the object class associated with a superposition fulfilling a predetermined criterion based on correlation results.

The invention refers to faster than Nyquist communication system wherein a set of symbols is conveyed from a transmitter (21) to a receiver (23), wherein the transmitter (21) and the receiver (23) are coupled by means of a transmission channel (22), comprising a precoder (210) adapted for generating a set of precoded symbols from a set of input symbols by performing a matrix operation with a precoding matrix, a pulse filter (212) adapted for generating a transmission signal to be transmitted over the transmission channel (22) as a function of the precoded symbols, a receiving filter (230) adapted for generating a set of sampled symbols as a function of the transmission signal and noise added by the transmission channel, and a decoder (232) adapted for generating a set of decoded symbols as a function of the set of sampled symbols, wherein the elements of the precoding matrix are dependent on a property of the pulse filter (212), The invention further refers to a transmitter, a receiver and corresponding methods, and to a user equipment and a base station.

The invention refers to faster than Nyquist communication system wherein a set of symbols is conveyed from a transmitter (21) to a receiver (23), wherein the transmitter (21) and the receiver (23) are coupled by means of a transmission channel (22), comprising a precoder (210) adapted for generating a set of precoded symbols from a set of input symbols by performing a matrix operation with a precoding matrix, a pulse filter (212) adapted for generating a transmission signal to be transmitted over the transmission channel (22) as a function of the precoded symbols, a receiving filter (230) adapted for generating a set of sampled symbols as a function of the transmission signal and noise added by the transmission channel, and a decoder (232) adapted for generating a set of decoded symbols as a function of the set of sampled symbols, wherein the elements of the precoding matrix are dependent on a property of the pulse filter (212), The invention further refers to a transmitter, a receiver and corresponding methods, and to a user equipment and a base station.