Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: Different solutions for an apparatus comprising a predictor predicting decodability of received symbols are disclosed. Decoding is performed based on the prediction.

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: Neural network-based structures for action user equipment device detection, estimation of time-of-arrival, and estimation of carrier frequency offset utilized with the narrowband physical random-access channel of wireless communication systems. The structure includes a neural network to generate predictions of active user equipment devices, and a twin neural network to generate time-of-arrival predictions for signals from the user equipment devices and carrier frequency offset predictions for signals from the user equipment devices.

Abstract: A system, apparatus, and method are provided for performing fast re-training of fully fused neural networks configured to implement at least a portion of a transceiver. At least one of a demapping module, an equalization module, or a channel estimation module can be implemented, at least in part, using a fully fused neural network. The neural network can be trained online during operation by acquiring training data sets using a number of received frames of data. Re-training of the neural network is performed periodically to adapt the neural network to changing channel characteristics. In various embodiments, a neural demapper, a neural channel estimator, and a neural receiver are disclosed to replace or augment one or more components of the transceiver. In another embodiment, an auto-encoder can be implemented across a transmitter and receiver to replace most of the components of the transceiver, the auto-encoder being trained via an end-to-end learning algorithm.

Abstract: Neural network performance is improved in terms of training speed and/or accuracy by encoding (mapping) inputs to the neural network into a higher dimensional space via a hash function. The input comprises coordinates used to identify a point within a d-dimensional space (e.g., 3D space). The point is quantized and a set of vertex coordinates corresponding to the point are input to a hash function. For example, for d=3, space may be partitioned into axis-aligned voxels of identical size and vertex coordinates of a voxel containing the point are input to the hash function to produce a set of encoded coordinates. The set of encoded coordinates is used to lookup D-dimensional feature vectors in a table of size T that have been learned. The learned feature vectors are filtered (e.g., linearly interpolated, etc.) based on the coordinates of the point to compute a feature vector corresponding to the point.

Abstract: A method and devices for configuring a data transmission network are disclosed.

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

Abstract: An apparatus, computer program and method is described including receiving data at a receiver of a communication system, generating an estimate of the data as transmitted by a transmitter of the transmission system (wherein generating the estimate includes a receiver algorithm having at least some trainable weights), generating a refined estimate of the transmitted data, based on said estimate and an error correction algorithm (wherein, in an operational mode, said estimate of the data as transmitted is generated based on the received data and said refined estimate); and generating, in the operational mode, a revised estimate of the transmitted data on each of a plurality of iterations of said generating an estimate of the transmitted data until a first condition is reached.

Abstract: Different solutions for an apparatus comprising a predictor predicting decodability of received symbols are disclosed. Decoding is performed based on the prediction.

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

Abstract: A method and devices for configuring a data transmission network are disclosed.