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.

IPC Classes  ?

• H04B 17/391 - Modelling the propagation channel
• G06N 3/047 - Probabilistic or stochastic networks
• G06N 3/08 - Learning methods
• G06N 20/00 - Machine learning
• H04L 27/00 - Modulated-carrier systems

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. One of the methods includes: determining first information; generating a first RF signal by processing the first information using an encoder machine-learning network of the first transceiver; transmitting the first RF signal from the first transceiver to a communications satellite or ground station through a first communication channel; receiving, from the communications satellite or ground station through a second communication channel, a second RF signal at a second transceiver; generating second information as a reconstruction of the first information by processing the second RF signal using a decoder machine-learning network of the second transceiver; calculating a measure of distance between the second information and the first information; and updating at least one of the encoder machine-learning network of the first transceiver or the decoder machine-learning network of the second transceiver.

IPC Classes  ?

• H04B 7/185 - Space-based or airborne stations
• G06N 20/00 - Machine learning
• H04B 17/318 - Received signal strength
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• H04B 17/345 - Interference values

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication. One of the methods includes: receiving an RF signal at a signal processing system for training a machine-learning network; providing the RF signal through the machine-learning network; producing an output from the machine-learning network; measuring a distance metric between the signal processing model output and a reference model output; determining modifications to the machine-learning network to reduce the distance metric between the output and the reference model output; and in response to reducing the distance metric to a value that is less than or equal to a threshold value, determining a score of the trained machine-learning network using one or more other RF signals and one or more other corresponding reference model outputs, the score indicating an a performance metric of the trained machine-learning network to perform the desired RF function.

IPC Classes  ?

• H04B 17/11 - MonitoringTesting of transmitters for calibration
• G06N 20/00 - Machine learning
• H04B 17/391 - Modelling the propagation channel
• H04W 24/08 - Testing using real traffic

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.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition
• H04W 24/08 - Testing using real traffic

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.

IPC Classes  ?

• H04B 17/391 - Modelling the propagation channel
• G06N 3/047 - Probabilistic or stochastic networks
• G06N 3/08 - Learning methods
• G06N 20/00 - Machine learning
• H04L 27/00 - Modulated-carrier systems

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. One or more rounds of updating the generator machine-learning network or the discriminator machine-learning network can allow the generator machine-learning network to produce information that is similar to the target information.

IPC Classes  ?

• G06N 3/088 - Non-supervised learning, e.g. competitive learning
• G06N 3/045 - Combinations of networks

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.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G01S 5/04 - Position of source determined by a plurality of spaced direction-finders
• G01S 7/40 - Means for monitoring or calibrating
• G01S 13/42 - Simultaneous measurement of distance and other coordinates
• G06N 3/08 - Learning methods
• G06N 3/084 - Backpropagation, e.g. using gradient descent
• G06N 20/20 - Ensemble learning
• H04B 17/318 - Received signal strength
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• H04B 17/391 - Modelling the propagation channel

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.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements
• G06N 3/044 - Recurrent networks, e.g. Hopfield networks
• G06N 3/08 - Learning methods
• G06N 3/084 - Backpropagation, e.g. using gradient descent
• G06N 20/00 - Machine learning
• H04B 17/391 - Modelling the propagation channel
• H04L 5/00 - Arrangements affording multiple use of the transmission path
• H04L 41/14 - Network analysis or design
• H04W 16/22 - Traffic simulation tools or models
• H04W 72/0453 - Resources in frequency domain, e.g. a carrier in FDMA

Abstract

A radio-frequency (RF) receiver includes: at least n antennas, where n is an integer greater than two; m processing channels configured to receive and process n RF signals from the at least n antennas, where m is an integer greater than one and less than n; a controller configured to cause a first processing channel of the m processing channels to receive, at different corresponding times, a plurality of RF signals of the n RF signals; an indexing module configured to receive outputs from the m processing channels, and generate one or more representations of the n RF signals based on the outputs; and a spatial estimation module configured to receive the one or more representations, execute a machine learning model based on the one or more representations, and determine, based on an output of the machine learning model, a spatial estimate for an emitter of the n RF signals.

IPC Classes  ?

• H04L 25/03 - Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
• H04L 25/02 - Baseband systems Details

Abstract

nnmnnmnmnmnnn RF signals.

IPC Classes  ?

• H04B 1/18 - Input circuits, e.g. for coupling to an antenna or a transmission line
• H04B 1/10 - Means associated with receiver for limiting or suppressing noise or interference
• H04B 1/28 - Circuits for superheterodyne receivers the receiver comprising at least one semiconductor device having three or more electrodes

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for placement and scheduling of radio signal processing dataflow operations. An example method provides a primitive radio signal processing computational dataflow graph that comprises nodes representing operations and directed edges representing data flow. The nodes and directed edges of the primitive radio signal processing computational dataflow graph are partitioned to produce a set of software kernels that, when executed on processing units of a target hardware platform, achieve a specific optimization objective. Runtime resource scheduling, including data placement for individual software kernels in the set of software kernels to efficiently execute operations on the processing units of the target hardware platform. The resources of the processing units in the target hardware platform are then allocated according to the defined runtime resource scheduling.

IPC Classes  ?

• H04W 16/18 - Network planning tools
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 17/11 - Complex mathematical operations for solving equations
• H04W 16/22 - Traffic simulation tools or models

Abstract

A method includes executing a radio frequency radiance field (RF-RF) model characterizing an environment; determining, based on outputs of the RF-RF model, one or more characteristics of a wireless channel between a first position and a second position in the environment; and controlling, based on the one or more characteristics of the wireless channel, an RF communication between the first position and the second position. RF-RF models can be used for RF control, communication systems testing and evaluation, system deployment, emitter localization, and other purposes.

IPC Classes  ?

• H04W 24/06 - Testing using simulated traffic
• H04W 28/16 - Central resource managementNegotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]

Abstract

A method includes executing a radio frequency radiance field (RF-RF) model characterizing an environment; determining, based on outputs of the RF-RF model, one or more characteristics of a wireless channel between a first position and a second position in the environment; and controlling, based on the one or more characteristics of the wireless channel, an RF communication between the first position and the second position. RF-RF models can be used for RF control, communication systems testing and evaluation, system deployment, emitter localization, and other purposes.

IPC Classes  ?

• H04W 24/00 - Supervisory, monitoring or testing arrangements
• H04W 4/00 - Services specially adapted for wireless communication networksFacilities therefor
• H04L 43/08 - Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• H04W 64/00 - Locating users or terminals for network management purposes, e.g. mobility management
• G06N 20/00 - Machine learning
• H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication. One of the methods includes: receiving an RF signal at a signal processing system for training a machine-learning network; providing the RF signal through the machine-learning network; producing an output from the machine-learning network; measuring a distance metric between the signal processing model output and a reference model output; determining modifications to the machine-learning network to reduce the distance metric between the output and the reference model output; and in response to reducing the distance metric to a value that is less than or equal to a threshold value, determining a score of the trained machine-learning network using one or more other RF signals and one or more other corresponding reference model outputs, the score indicating an a performance metric of the trained machine-learning network to perform the desired RF function.

IPC Classes  ?

• H04B 17/11 - MonitoringTesting of transmitters for calibration
• G06N 20/00 - Machine learning
• H04B 17/391 - Modelling the propagation channel
• H04W 24/08 - Testing using real traffic

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. One of the methods includes: determining first information; generating a first RF signal by processing the first information using an encoder machine-learning network of the first transceiver; transmitting the first RF signal from the first transceiver to a communications satellite or ground station through a first communication channel; receiving, from the communications satellite or ground station through a second communication channel, a second RF signal at a second transceiver; generating second information as a reconstruction of the first information by processing the second RF signal using a decoder machine-learning network of the second transceiver; calculating a measure of distance between the second information and the first information; and updating at least one of the encoder machine-learning network of the first transceiver or the decoder machine-learning network of the second transceiver.

IPC Classes  ?

• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• G06N 20/00 - Machine learning
• H04B 7/185 - Space-based or airborne stations
• H04B 17/318 - Received signal strength
• H04B 17/345 - Interference values

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.

IPC Classes  ?

• H04B 1/16 - Circuits
• G06N 3/0455 - Auto-encoder networksEncoder-decoder networks
• G06N 3/0895 - Weakly supervised learning, e.g. semi-supervised or self-supervised learning

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.

IPC Classes  ?

• H04B 7/06 - Diversity systemsMulti-antenna systems, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
• G06N 20/20 - Ensemble learning
• H04B 17/309 - Measuring or estimating channel quality parameters
• H04B 7/0413 - MIMO systems
• H04B 17/373 - Predicting channel quality parameters
• H04L 25/02 - Baseband systems Details

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.

IPC Classes  ?

• G06N 3/045 - Combinations of networks
• G06N 3/08 - Learning methods
• H04L 25/02 - Baseband systems Details
• H04L 27/26 - Systems using multi-frequency codes

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting distortion of radio signals A transmit radio signal corresponding to an output of a transmitting radio signal processing system is obtained. A pre-distorted radio signal is then generated by processing the transmit radio signal using a nonlinear pre-distortion machine learning model. The nonlinear pre-distortion machine learning model includes model parameters and at least one nonlinear function to correct radio signal distortion or interference. A transmit output radio signal is obtained by processing the pre-distorted radio signal through the transmitting radio signal processing system. The transmit output radio signal is then transmitted to one or more radio receivers.

IPC Classes  ?

• H04B 1/04 - Circuits
• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods
• H04W 88/08 - Access point devices

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.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]

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.

IPC Classes  ?

• H04W 72/541 - Allocation or scheduling criteria for wireless resources based on quality criteria using the level of interference
• H04B 1/10 - Means associated with receiver for limiting or suppressing noise or interference
• G06N 20/00 - Machine learning
• H04W 24/02 - Arrangements for optimising operational condition
• H04W 48/16 - DiscoveringProcessing access restriction or access information
• H04W 72/27 - Control channels or signalling for resource management between access points
• H04W 72/54 - Allocation or scheduling criteria for wireless resources based on quality criteria

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.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G01S 5/04 - Position of source determined by a plurality of spaced direction-finders
• G01S 7/40 - Means for monitoring or calibrating
• G01S 13/42 - Simultaneous measurement of distance and other coordinates
• G06N 3/08 - Learning methods
• G06N 3/084 - Backpropagation, e.g. using gradient descent
• G06N 20/20 - Ensemble learning
• H04B 17/318 - Received signal strength
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• H04B 17/391 - Modelling the propagation channel

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication. One of the methods includes: receiving an RF signal at a signal processing system for training a machine-learning network; providing the RF signal through the machine-learning network; producing an output from the machine-learning network; measuring a distance metric between the signal processing model output and a reference model output; determining modifications to the machine-learning network to reduce the distance metric between the output and the reference model output; and in response to reducing the distance metric to a value that is less than or equal to a threshold value, determining a score of the trained machine-learning network using one or more other RF signals and one or more other corresponding reference model outputs, the score indicating an a performance metric of the trained machine-learning network to perform the desired RF function.

IPC Classes  ?

• H04B 17/11 - MonitoringTesting of transmitters for calibration
• H04W 24/08 - Testing using real traffic
• H04B 17/391 - Modelling the propagation channel
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• G06N 3/08 - Learning methods
• H04B 17/391 - Modelling the propagation channel

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.

IPC Classes  ?

• G06N 20/00 - Machine learning
• H04B 17/391 - Modelling the propagation channel
• G06N 3/08 - Learning methods

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.

IPC Classes  ?

• G01S 3/02 - Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received using radio waves
• G06N 3/02 - Neural networks
• G01S 3/06 - Means for increasing effective directivity, e.g. by combining signals having differently-oriented directivity characteristics or by sharpening the envelope waveform of the signal derived from a rotating or oscillating beam antenna
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G01S 5/06 - Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
• G06F 30/20 - Design optimisation, verification or simulation
• G06N 3/08 - Learning methods
• G06N 3/10 - Interfaces, programming languages or software development kits, e.g. for simulating neural networks
• G01S 3/14 - Systems for determining direction or deviation from predetermined direction
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition
• H04W 24/08 - Testing using real traffic

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. One of the methods includes: determining first information; generating a first RF signal by processing the first information using an encoder machine-learning network of the first transceiver; transmitting the first RF signal from the first transceiver to a communications satellite or ground station through a first communication channel; receiving, from the communications satellite or ground station through a second communication channel, a second RF signal at a second transceiver; generating second information as a reconstruction of the first information by processing the second RF signal using a decoder machine-learning network of the second transceiver; calculating a measure of distance between the second information and the first information; and updating at least one of the encoder machine-learning network of the first transceiver or the decoder machine-learning network of the second transceiver.

IPC Classes  ?

• H04B 17/345 - Interference values
• H04B 7/185 - Space-based or airborne stations
• H04B 17/318 - Received signal strength
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• H04W 56/00 - Synchronisation arrangements
• G06N 3/044 - Recurrent networks, e.g. Hopfield networks
• G06N 3/08 - Learning methods
• G06N 3/084 - Backpropagation, e.g. using gradient descent
• G06N 20/00 - Machine learning
• H04B 17/391 - Modelling the propagation channel
• H04L 5/00 - Arrangements affording multiple use of the transmission path
• H04L 41/14 - Network analysis or design
• H04W 16/22 - Traffic simulation tools or models
• H04W 72/0453 - Resources in frequency domain, e.g. a carrier in FDMA

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for detecting and classifying radio signals. The method includes obtaining one or more radio frequency (RF) snapshots corresponding to a first set of signals from a first RF source; generating a first training data set based on the one or more RF snapshots; annotating the first training data set to generate an annotated first training data set; generating a trained detection and classification model based on the annotated first training data set; and providing the trained detection and classification model to a sensor engine to detect and classify one or more new signals using the trained detection and classification model.

IPC Classes  ?

• G01R 29/08 - Measuring electromagnetic field characteristics
• G06N 3/08 - Learning methods
• B64C 39/02 - Aircraft not otherwise provided for characterised by special use

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for detecting and classifying radio signals. The method includes obtaining one or more radio frequency (RF) snapshots corresponding to a first set of signals from a first RF source; generating a first training data set based on the one or more RF snapshots; annotating the first training data set to generate an annotated first training data set; generating a trained detection and classification model based on the annotated first training data set; and providing the trained detection and classification model to a sensor engine to detect and classify one or more new signals using the trained detection and classification model.

IPC Classes  ?

• G06N 20/00 - Machine learning
• G10L 25/18 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
• G10L 25/51 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination
• H04R 29/00 - Monitoring arrangementsTesting arrangements

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. One of the methods includes: determining first information; generating a first RF signal by processing the first information using an encoder machine-learning network of the first transceiver; transmitting the first RF signal from the first transceiver to a communications satellite or ground station through a first communication channel; receiving, from the communications satellite or ground station through a second communication channel, a second RF signal at a second transceiver; generating second information as a reconstruction of the first information by processing the second RF signal using a decoder machine-learning network of the second transceiver; calculating a measure of distance between the second information and the first information; and updating at least one of the encoder machine-learning network of the first transceiver or the decoder machine-learning network of the second transceiver.

IPC Classes  ?

• H04B 17/345 - Interference values
• H04B 7/185 - Space-based or airborne stations
• G06N 20/00 - Machine learning
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• H04B 17/318 - Received signal strength

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication. One of the methods includes: receiving an RF signal at a signal processing system for training a machine-learning network; providing the RF signal through the machine-learning network; producing an output from the machine-learning network; measuring a distance metric between the signal processing model output and a reference model output; determining modifications to the machine-learning network to reduce the distance metric between the output and the reference model output; and in response to reducing the distance metric to a value that is less than or equal to a threshold value, determining a score of the trained machine-learning network using one or more other RF signals and one or more other corresponding reference model outputs, the score indicating an a performance metric of the trained machine-learning network to perform the desired RF function.

IPC Classes  ?

• H04B 17/11 - MonitoringTesting of transmitters for calibration
• H04W 24/08 - Testing using real traffic
• H04B 17/391 - Modelling the propagation channel
• G06N 20/00 - Machine learning

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting distortion of radio signals A transmit radio signal corresponding to an output of a transmitting radio signal processing system is obtained. A pre-distorted radio signal is then generated by processing the transmit radio signal using a nonlinear pre-distortion machine learning model. The nonlinear pre-distortion machine learning model includes model parameters and at least one nonlinear function to correct radio signal distortion or interference. A transmit output radio signal is obtained by processing the pre-distorted radio signal through the transmitting radio signal processing system. The transmit output radio signal is then transmitted to one or more radio receivers.

IPC Classes  ?

• H04B 1/04 - Circuits
• G06N 3/08 - Learning methods
• G06N 3/04 - Architecture, e.g. interconnection topology
• H04W 88/08 - Access point devices

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for placement and scheduling of radio signal processing dataflow operations. An example method provides a primitive radio signal processing computational dataflow graph that comprises nodes representing operations and directed edges representing data flow. The nodes and directed edges of the primitive radio signal processing computational dataflow graph are partitioned to produce a set of software kernels that, when executed on processing units of a target hardware platform, achieve a specific optimization objective. Runtime resource scheduling, including data placement for individual software kernels in the set of software kernels to efficiently execute operations on the processing units of the target hardware platform. The resources of the processing units in the target hardware platform are then allocated according to the defined runtime resource scheduling.

IPC Classes  ?

• G06F 9/455 - EmulationInterpretationSoftware simulation, e.g. virtualisation or emulation of application or operating system execution engines
• H04W 16/18 - Network planning tools
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 17/11 - Complex mathematical operations for solving equations
• H04W 16/22 - Traffic simulation tools or models

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.

IPC Classes  ?

• H04B 17/391 - Modelling the propagation channel
• H04L 27/00 - Modulated-carrier systems
• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• H04B 17/391 - Modelling the propagation channel
• H04L 27/00 - Modulated-carrier systems
• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• H04L 27/26 - Systems using multi-frequency codes
• H04L 27/28 - Systems using multi-frequency codes with simultaneous transmission of different frequencies each representing one code element

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over RF channels. One of the methods includes: determining first information; generating a first RF signal by processing the first information using an encoder machine-learning network of the first transceiver; transmitting the first RF signal from the first transceiver to a communications satellite or ground station through a first communication channel; receiving, from the communications satellite or ground station through a second communication channel, a second RF signal at a second transceiver; generating second information as a reconstruction of the first information by processing the second RF signal using a decoder machine-learning network of the second transceiver; calculating a measure of distance between the second information and the first information; and updating at least one of the encoder machine-learning network of the first transceiver or the decoder machine-learning network of the second transceiver.

IPC Classes  ?

• H04B 17/345 - Interference values
• H04B 7/185 - Space-based or airborne stations
• H04B 17/318 - Received signal strength
• H04B 17/336 - Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
• G06N 20/00 - Machine learning

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. One or more rounds of updating the generator machine-learning network or the discriminator machine-learning network can allow the generator machine-learning network to produce information that is similar to the target information.

IPC Classes  ?

• G06N 3/088 - Non-supervised learning, e.g. competitive learning
• G06N 3/045 - Combinations of networks

Goods & Services

downloadable software for detecting signal information incorporating machine learning; downloadable software development kits; recorded software for detecting signal information incorporating machine learning software as a service featuring software for detecting signal information incorporating machine learning

Goods & Services

downloadable software for communications signal processing incorporating machine learning; recorded software for communications signal processing incorporating machine learning; downloadable software development kits software as a service featuring software for communications signal processing incorporating machine learning

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.

IPC Classes  ?

• G06N 7/01 - Probabilistic graphical models, e.g. probabilistic networks
• G06F 16/906 - ClusteringClassification
• G06N 3/047 - Probabilistic or stochastic networks
• G06N 20/00 - Machine learning
• H04B 17/00 - MonitoringTesting

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.

IPC Classes  ?

• H04W 24/02 - Arrangements for optimising operational condition
• H04W 24/08 - Testing using real traffic
• G06N 20/00 - Machine learning
• H04W 24/04 - Arrangements for maintaining operational condition

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.

IPC Classes  ?

• H04L 12/24 - Arrangements for maintenance or administration
• H04W 16/22 - Traffic simulation tools or models
• H04B 17/391 - Modelling the propagation channel
• G06N 3/08 - Learning methods
• H04W 56/00 - Synchronisation arrangements
• G06N 20/00 - Machine learning
• H04L 5/00 - Arrangements affording multiple use of the transmission path
• H04W 72/04 - Wireless resource allocation
• H04L 41/14 - Network analysis or design
• G06N 3/04 - Architecture, e.g. interconnection topology

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting distortion of radio signals A transmit radio signal corresponding to an output of a transmitting radio signal processing system is obtained. A pre-distorted radio signal is then generated by processing the transmit radio signal using a nonlinear pre-distortion machine learning model. The nonlinear pre-distortion machine learning model includes model parameters and at least one nonlinear function to correct radio signal distortion or interference. A transmit output radio signal is obtained by processing the pre-distorted radio signal through the transmitting radio signal processing system. The transmit output radio signal is then transmitted to one or more radio receivers.

IPC Classes  ?

• H04B 1/04 - Circuits
• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods
• H04W 88/08 - Access point devices

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over radio frequency (RF) channels. One of the methods includes: determining first information; generating a first RF signal by processing using an encoder machine-learning network; determining a second RF signal that represents the first RF signal altered by transmission through a communication channel; determining a first property of the first signal or the second RF signal; calculating a first measure of distance between a target value of the first property and an actual value of the first or second RF signal; generating second information as a reconstruction of the first information using a decoder machine-learning network; calculating a second measure of distance between the first information and the second information; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on the first and second measures.

IPC Classes  ?

• G01S 5/00 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G01S 11/06 - Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
• G06N 20/00 - Machine learning

Abstract

Methods and systems including computer programs encoded on computer storage media, for training and deploying machine-learned communication over radio frequency (RF) channels. One of the methods includes: determining first information; generating a first RF signal by processing using an encoder machine-learning network; determining a second RF signal that represents the first RF signal altered by transmission through a communication channel; determining a first property of the first signal or the second RF signal; calculating a first measure of distance between a target value of the first property and an actual value of the first or second RF signal; generating second information as a reconstruction of the first information using a decoder machine-learning network; calculating a second measure of distance between the first information and the second information; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on the first and second measures.

IPC Classes  ?

• G01S 5/00 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations
• G01S 5/02 - Position-fixing by co-ordinating two or more direction or position-line determinationsPosition-fixing by co-ordinating two or more distance determinations using radio waves
• G01S 11/06 - Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
• G06N 20/00 - Machine learning

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.

IPC Classes  ?

• G06N 3/08 - Learning methods
• G06N 3/10 - Interfaces, programming languages or software development kits, e.g. for simulating neural networks
• H04W 72/06 - Wireless resource allocation based on ranking criteria of the wireless resources
• H04W 72/08 - Wireless resource allocation based on quality criteria
• H04W 72/10 - Wireless resource allocation based on priority criteria

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.

IPC Classes  ?

• G06N 3/08 - Learning methods
• H04W 16/22 - Traffic simulation tools or models
• H04W 56/00 - Synchronisation arrangements
• G06N 20/00 - Machine learning
• H04L 5/00 - Arrangements affording multiple use of the transmission path
• H04W 72/04 - Wireless resource allocation
• H04B 17/391 - Modelling the propagation channel
• H04L 12/24 - Arrangements for maintenance or administration

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for placement and scheduling of radio signal processing dataflow operations. An example method provides a primitive radio signal processing computational dataflow graph that comprises nodes representing operations and directed edges representing data flow. The nodes and directed edges of the primitive radio signal processing computational dataflow graph are partitioned to produce a set of software kernels that, when executed on processing units of a target hardware platform, achieve a specific optimization objective. Runtime resource scheduling, including data placement for individual software kernels in the set of software kernels are performed to efficiently execute operations on the processing units of the target hardware platform. The resources of the processing units in the target hardware platform are then allocated according to the defined runtime resource scheduling.

IPC Classes  ?

• G06F 9/46 - Multiprogramming arrangements
• H04W 16/18 - Network planning tools
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 17/11 - Complex mathematical operations for solving equations
• H04W 16/22 - Traffic simulation tools or models

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for placement and scheduling of radio signal processing dataflow operations. An example method provides a primitive radio signal processing computational dataflow graph that comprises nodes representing operations and directed edges representing data flow. The nodes and directed edges of the primitive radio signal processing computational dataflow graph are partitioned to produce a set of software kernels that, when executed on processing units of a target hardware platform, achieve a specific optimization objective. Runtime resource scheduling, including data placement for individual software kernels in the set of software kernels to efficiently execute operations on the processing units of the target hardware platform. The resources of the processing units in the target hardware platform are then allocated according to the defined runtime resource scheduling.

IPC Classes  ?

• G06F 9/46 - Multiprogramming arrangements
• H04W 16/18 - Network planning tools
• G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
• G06F 17/11 - Complex mathematical operations for solving equations
• H04W 16/22 - Traffic simulation tools or models

Goods & Services

Research and development of computer software