Abstract: A method includes maintaining a set of parameters or weights derived through online learning for a neural net; transmitting an update of the parameters or weights to a decoder; deriving a first prediction block based on an output of the neural net using the parameters or weights; deriving a first encoded prediction error block through encoding a difference of the first prediction block and a first input block; encoding the first encoded prediction error block into a bitstream; deriving a reconstructed prediction error block based on the first encoded prediction error block; deriving a second prediction block based on an output of the neural net using the parameters or weights and the reconstructed prediction error block; deriving a second encoded prediction error block through encoding a difference of the second prediction block and a second input block; and encoding the second encoded prediction error block into a bitstream.

Abstract: A method, apparatus and computer program, the method comprising: receiving a first biopotential signal obtained by a first capacitive sensor; receiving a second biopotential signal obtained by a second capacitive sensor, the first capacitive sensor and the second capacitive sensor being positioned at different locations on a subject; synchronising biopotential signals obtained by the first capacitive sensor and the second capacitive sensor by applying a time adjustment to biopotential signals obtained by at least one of the first capacitive sensor or the second capacitive sensor; wherein features in at least one of the first biopotential signal and the second biopotential signal are used to synchronise the biopotential signals obtained by the first capacitive sensor and the second capacitive sensor.

Abstract: This document discloses a solution for detecting interference in a radio access network. According to an aspect, a method includes as performed by a network node of the radio access network: acquiring a first equalized signal representing a signal received by a first radio head serving a terminal device, the first equalized signal including a signal received by the first radio head from the terminal device; acquiring a second equalized signal representing a signal received by a second radio head not serving the terminal device, wherein the second radio head is spatially distant from the first radio head; cross-correlating the first equalized signal with the second equalized signal and determining, on the basis of said cross-correlating, whether or not the second equalized signal also includes a signal received from the terminal device; and as a result of the second equalized signal being determined to include the signal received from the terminal device, causing execution of an interference management action.

Abstract: An apparatus, method and SW for HARQ control are disclosed. The method includes: inputting (504) a beginning part of a data packet received on a specific frequency band and in a scheduled slot between a user apparatus and a radio access network, and supplementary data related to the data packet, into a neural network with trained parameters to predict a success of decoding the data packet after received in full; and controlling (516) a hybrid automatic repeat request procedure associated with the data packet based on the predicted success using the specific frequency band and the scheduled slot for full-duplex inband signalling.

Abstract: An apparatus, method and SW for HARQ control are disclosed. The method includes: analyzing (514) a beginning part of a data packet received on a specific frequency band and in a scheduled slot between a user apparatus and a radio access network to predict a success of decoding the data packet after received in full; and controlling (516) a hybrid automatic repeat request procedure associated with the data packet based on the predicted success using the specific frequency band and the scheduled slot for full-duplex inband signaling.

Abstract: The embodiments relate to a method comprising compressing input data (I) by means of at least a neural network (E, 310); determining a compression rate for data compression; miming the neural network (E, 310) with the input data (I) to produce an output data (c); removing a number of elements from the output data (c) according to the compression rate to result in a reduced form of the output data (me); and providing the reduced form of the output data (me) and the compression rate to a decoder (D, 320). The embodiments also relate to a method comprising receiving input data (me) for decompression; decompressing the input data (me) by means of at least a neural network (D, 320); determining a decompression rate for decompressing the input data (me); miming the neural network (D, 320) with input data (me) to produce a decompressed output data (ï); padding a number of elements to the compressed input data (me) according to the decompression rate to produce an output data (ï); and providing the output data (ï).

Abstract: A method includes maintaining a set of parameters or weights derived through online learning for a neural net; transmitting an update of the parameters or weights to a decoder; deriving a first prediction block based on an output of the neural net using the parameters or weights; deriving a first encoded prediction error block through encoding a difference of the first prediction block and a first input block; encoding the first encoded prediction error block into a bitstream; deriving a reconstructed prediction error block based on the first encoded prediction error block; deriving a second prediction block based on an output of the neural net using the parameters or weights and the reconstructed prediction error block; deriving a second encoded prediction error block through encoding a difference of the second prediction block and a second input block; and encoding the second encoded prediction error block into a bitstream.

Abstract: This document discloses a solution for detecting interference in a radio access network. According to an aspect, a method includes as performed by a network node of the radio access network: acquiring a first equalized signal representing a signal received by a first radio head serving a terminal device, the first equalized signal including a signal received by the first radio head from the terminal device; acquiring a second equalized signal representing a signal received by a second radio head not serving the terminal device, wherein the second radio head is spatially distant from the first radio head; cross-correlating the first equalized signal with the second equalized signal and determining, on the basis of said cross-correlating, whether or not the second equalized signal also includes a signal received from the terminal device; and as a result of the second equalized signal being determined to include the signal received from the terminal device, causing execution of an interference management action.

Abstract: An approach is provided for synchronizing an impedance cardiography (“ICG”) measurement period with an electrocardiography (“ECG”) signal to reduce patient (105) auxiliary current. The approach involves measuring an ECG signal of a patient via an ECG device (103). The approach also involves processing the ECG signal to cause, at least in part, a detection of one or more ECG features of the signal. The approach further involves synchronizing a start, a stop, or a combination thereof of a measurement of an ICG signal of the patient via an ICG device (101) based, at least in part, on the detection of the one or more ECG features. The measurement of the ICG signal includes injecting an electrical current into the patient (105) for a duration of the measurement.

Abstract: Systems, apparatuses, and methods are described for configuring denoising models based on machine learning. A denoising model (301) may remove noise from data samples (451). A noise model (403) may include noise in the data samples. Data samples processed by the denoising model (453) and/or the noise model (455) and original data samples (457) may be input into a discriminator (405). The discriminator may make determinations to classify input data samples. The denoising model and/or the discriminator may be trained based on the determinations.

Abstract: A method comprising: deriving a first prediction block (608) at least partly based on an output of a neural net (602) using a first set of parameters; deriving a first encoded prediction error block (614-620) through encoding a difference of the first prediction block and a first input block; encoding (620) the first encoded prediction error block into a bitstream; deriving a first reconstructed prediction error block (624) from the first encoded prediction error block; deriving a training signal (628) from one or both of the first encoded prediction error block and/or the first reconstructed prediction error block (624); retraining (630) the neural net (602) with the training signal (628) to obtain a second set of parameters for the neural net (602); deriving a second prediction block (608) at least partly based on an output of the neural net using the second set of parameters; deriving a second encoded prediction error block (614-620) through encoding a difference of the second prediction block and a second

Abstract: An apparatus configured to generate an output quality error estimate using a machine-learning error estimation model to compare an output meeting a predetermined quality threshold with an output image reconstructed from a plurality of images, and provide the output quality error estimate for use in estimating if a second subsequent image is required, in addition to a first subsequent image to obtain a cumulative output having an output quality error meeting a predetermined error threshold. Also an apparatus configured, using a received output quality error estimate generated using a machine-learning error estimation model as above, to estimate if a second subsequent image is required, in addition to a first subsequent image, to obtain a cumulative output having an output quality error meeting a predetermined error threshold.

Abstract: The invention relates to a method, an apparatus and a computer program product for analyzing media content. The method comprises receiving media content; performing feature extraction of the media content at a plurality of convolution layers to produce a plurality of layer-specific feature maps; transmitting from the plurality of convolution layers a corresponding layer-specific feature map to a corresponding de-convolution layer of a plurality of de-convolution layers via a recurrent connection between the plurality of convolution layers and the plurality of de-convolution layers; and generating a reconstructed media content based on the plurality of feature maps.

Abstract: A method comprising: deriving a first prediction block (608) at least partly based on an output of a neural net (602) using a first set of parameters; deriving a first encoded prediction error block (614-620) through encoding a difference of the first prediction block and a first input block; encoding (620) the first encoded prediction error block into a bitstream; deriving a first reconstructed prediction error block (624) from the first encoded prediction error block; deriving a training signal (628) from one or both of the first encoded prediction error block and/or the first reconstructed prediction error block (624); retraining (630) the neural net (602) with the training signal (628) to obtain a second set of parameters for the neural net (602); deriving a second prediction block (608) at least partly based on an output of the neural net using the second set of parameters; deriving a second encoded prediction error block (614-620) through encoding a difference of the second prediction block and a second

Abstract: A method of detection of a recurrent feature of interest within a signal including: obtaining evidence, based on a signal, the evidence including a probability density function for each of a plurality of parameters for parameterizing the signal, including at least one probability density function for a parameter, of the plurality of parameters, that positions a feature of interest within signal data of the signal; parameterizing a portion of the signal data from the signal based upon a hypothesis that a point of interest in the signal data is a position of the feature of interest; determining a posterior probability of the hypothesis being true given the portion of the signal data by combining a prior probability of the hypothesis and a conditional probability of observing the portion of the signal data given the hypothesis.

Abstract: The invention relates to a method comprising receiving a set of input samples, said set of input images comprising real images and generated images; extracting a set of feature maps from multiple layers of a pre-trained neural network for both the real images and the generated images; determining statistics for each feature map of the set of feature maps; comparing statistics of the feature maps for the real images to statistics of the feature maps for the generated images by using a distance function to obtain a vector of distances; and averaging the distances of the vector of distances to have a value indicating a diversity of the generated images. The invention also relates to technical equipment for implementing the method.

Abstract: A method, apparatus and computer program, the method comprising: receiving a first biopotential signal obtained by a first capacitive sensor; receiving a second biopotential signal obtained by a second capacitive sensor, the first capacitive sensor and the second capacitive sensor being positioned at different locations on a subject; synchronising biopotential signals obtained by the first capacitive sensor and the second capacitive sensor by applying a time adjustment to biopotential signals obtained by at least one of the first capacitive sensor or the second capacitive sensor; wherein features in at least one of the first biopotential signal and the second biopotential signal are used to synchronise the biopotential signals obtained by the first capacitive sensor and the second capacitive sensor.

Abstract: A method includes accessing, by at least one processing device, an audible signal including at least one in-ear microphone audible signal and at least one external microphone audible signal and at least one noise signal; training a generative network to generate an enhanced external microphone signal from an in-ear microphone signal based on the at least one in-ear microphone audible signal and the at least one external microphone audible signal; and outputting the generative network.

Abstract: Methods and apparatus, including computer program products, are provided for receiving, at a bidirectional recurrent neural network, a music file preprocessed to include at least one token data inserted within at least one location in the music file in order to enable varying the music file; generating, by the bidirectional recurrent neural network, an output music file, wherein the bidirectional recurrent neural network generates music data to replace the at least one token data; and providing, by the bidirectional recurrent neural network, the output music file representing a varied version of the music file. Related apparatus, systems, methods, and articles are also described.

Abstract: An apparatus configured to generate an output quality error estimate using a machine-learning error estimation model to in compare an output meeting a predetermined quality threshold with an output image reconstructed from a plurality of images, and provide the output quality error estimate for use in estimating if a second subsequent image is required, in addition to a first subsequent image to obtain a cumulative output having an output quality error meeting a predetermined error threshold. Also an apparatus configured, using a received output quality error estimate generated using a machine-learning error estimation model as above, to estimate if a second subsequent image is required, in addition to a first subsequent image, to obtain a cumulative output having an output quality error meeting a predetermined error threshold.