Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for radio frequency band segmentation, signal detection and labelling using machine learning. In some implementations, a sample of electromagnetic energy processed by one or more radio frequency (RF) communication receivers is received from the one or more receivers. The sample of electromagnetic energy is examined to detect one or more RF signals present in the sample. In response to detecting one or more RF signals present in the sample, the one or more RF signals are extracted from the sample, and time and frequency bounds are estimated for each of the one or more RF signals. For each of the one or more RF signals, at least one of a type of a signal present, or a likelihood of signal being present, in the sample is classified.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for characterizing radio propagation channels. One method includes receiving, at a first modem, a first unit of communication over a radio frequency (RF) communication path from a second modem, wherein the first modem and the second modem process information for RF communications. The first modem identifies fields in the first unit of communication, the fields used to analyze the RF communication path. The first modem extracts data from the fields. The first modem accesses a channel model for approximating a channel representative of the RF communication path from the first modem to the second modem, wherein the channel model includes machine learning models. The first modem trains the channel model using the extracted data. The first modem applies the trained channel model to simulate a set of channel effects associated with the communication path.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for adversarially generated communication. In some implementations, first information is used as input for a generator machine-learning network. Information is taken from both the generator machine-learning network and target information that includes sample signals or other data. The information is sent to a discriminator machine-learning network which produces decision information including whether the information originated from the generator machine-learning network or the target information. An optimizer takes the decision information and performs one or more iterative optimization techniques which help determine updates to the generator machine-learning network or the discriminator machine-learning network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for positioning a radio signal receiver at a first location within a three dimensional space; positioning a transmitter at a second location within the three dimensional space; transmitting a transmission signal from the transmitter to the radio signal receiver; processing, using a machine-learning network, one or more parameters of the transmission signal received at the radio signal receiver; in response to the processing, obtaining, from the machine-learning network, a prediction corresponding to a direction of arrival of the transmission signal transmitted by the transmitter; computing an error term by comparing the prediction to a set of ground truths; and updating the machine-learning network based on the error term.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. In some implementations, information is obtained. An encoder network is used to process the information and generate a first RF signal. The first RF signal is transmitted through a first channel. A second RF signal is determined that represents the first RF signal having been altered by transmission through the first channel. Transmission of the first RF signal is simulated over a second channel implementing a machine-learning network, the second channel representing a model of the first channel. A simulated RF signal that represents the first RF signal having been altered by simulated transmission through the second channel is determined. A measure of distance between the second RF signal and the simulated RF signal is calculated. The machine-learning network is updated using the measure of distance.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for adversarially generated communication. In some implementations, first information is used as input for a generator machine-learning network. Information is taken from both the generator machine-learning network and target information that includes sample signals or other data. The information is sent to a discriminator machine-learning network which produces decision information including whether the information originated from the generator machine-learning network or the target information. An optimizer takes the decision information and performs one or more iterative optimization techniques which help determine updates to the generator machine-learning network or the discriminator machine-learning network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for positioning a radio signal receiver at a first location within a three dimensional space; positioning a transmitter at a second location within the three dimensional space; transmitting a transmission signal from the transmitter to the radio signal receiver; processing, using a machine-learning network, one or more parameters of the transmission signal received at the radio signal receiver; in response to the processing, obtaining, from the machine-learning network, a prediction corresponding to a direction of arrival of the transmission signal transmitted by the transmitter; computing an error term by comparing the prediction to a set of ground truths; and updating the machine-learning network based on the error term.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for characterizing radio propagation channels. One method includes receiving, at a first modem, a first unit of communication over a radio frequency (RF) communication path from a second modem, wherein the first modem and the second modem process information for RF communications. The first modem identifies fields in the first unit of communication, the fields used to analyze the RF communication path. The first modem extracts data from the fields. The first modem accesses a channel model for approximating a channel representative of the RF communication path from the first modem to the second modem, wherein the channel model includes machine learning models. The first modem trains the channel model using the extracted data. The first modem applies the trained channel model to simulate a set of channel effects associated with the communication path.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. In some implementations, information is obtained. An encoder network is used to process the information and generate a first RF signal. The first RF signal is transmitted through a first channel. A second RF signal is determined that represents the first RF signal having been altered by transmission through the first channel. Transmission of the first RF signal is simulated over a second channel implementing a machine-learning network, the second channel representing a model of the first channel. A simulated RF signal that represents the first RF signal having been altered by simulated transmission through the second channel is determined. A measure of distance between the second RF signal and the simulated RF signal is calculated. The machine-learning network is updated using the measure of distance.

Abstract: A method for processing radio frequency (RF) signals is provided. The method includes receiving one or more RF signals from one or more antenna channels. The method includes obtaining, from the one or more RF signals, a plurality of unlabeled data samples. The method includes generating an input tensor representation of the plurality of data samples. The method includes pretraining a first machine learning network using the input tensor representation to obtain one or more embeddings. The method includes training a second machine learning network using the one or more embeddings. The second machine learning network is configured to perform one or more signal processing tasks. Also provided is a system having an antenna array and one or more processors.

Abstract: A method includes obtaining samples of radio-frequency (RF) uplink data signals received wirelessly at a radio unit of a radio access network, the RF uplink data signals including a first RF uplink data signal received from a user device; providing the samples of the RF uplink data signals as input to at least one machine learning model; in response to providing the samples of the RF uplink data signals as input to the at least one machine learning model, obtaining based on an output of the at least one machine learning model, recovered data of the RF uplink data signals; and sending the recovered data of the RF uplink signals to a destination device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

Abstract: A method includes obtaining, using a specified protocol of a radio access network, low-level signal data corresponding to a radio frequency (RF) signal processed in the radio access network; providing the low-level signal data as input to at least one machine learning network; in response to providing the low-level signal data as input to the at least one machine learning network, obtaining, as an output of the at least one machine learning network, metadata providing information on one or more characteristics of the RF signal; and controlling an operation of the radio access network based on the metadata.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for positioning a radio signal receiver at a first location within a three dimensional space; positioning a transmitter at a second location within the three dimensional space; transmitting a transmission signal from the transmitter to the radio signal receiver; processing, using a machine-learning network, one or more parameters of the transmission signal received at the radio signal receiver; in response to the processing, obtaining, from the machine-learning network, a prediction corresponding to a direction of arrival of the transmission signal transmitted by the transmitter; computing an error term by comparing the prediction to a set of ground truths; and updating the machine-learning network based on the error term.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for providing one or more values from a distribution of values to a neural network trained to generate simulated channel responses corresponding to one or more radio frequency (RF) communication channels; and obtaining an output of the neural network based on processing the one or more values by the neural network, the output indicating a simulated channel response corresponding to at least one communication channel of the one or more RF communication channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for characterizing radio propagation channels. One method includes receiving, at a first modem, a first unit of communication over a radio frequency (RF) communication path from a second modem, wherein the first modem and the second modem process information for RF communications. The first modem identifies fields in the first unit of communication, the fields used to analyze the RF communication path. The first modem extracts data from the fields. The first modem accesses a channel model for approximating a channel representative of the RF communication path from the first modem to the second modem, wherein the channel model includes machine learning models. The first modem trains the channel model using the extracted data. The first modem applies the trained channel model to simulate a set of channel effects associated with the communication path.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. In some implementations, information is obtained. An encoder network is used to process the information and generate a first RF signal. The first RF signal is transmitted through a first channel. A second RF signal is determined that represents the first RF signal having been altered by transmission through the first channel. Transmission of the first RF signal is simulated over a second channel implementing a machine-learning network, the second channel representing a model of the first channel. A simulated RF signal that represents the first RF signal having been altered by simulated transmission through the second channel is determined. A measure of distance between the second RF signal and the simulated RF signal is calculated. The machine-learning network is updated using the measure of distance.