Signal de-mapping

Abstract

Aspects and embodiments provide apparatus and methods that may be used to assist in selecting one of a plurality of available receiver configurations to demap a received signal at a receiver in a wireless communication network. The described apparatus may include trainable logic that may take the form of a neural network. The trainable logic is configured to quantify a plurality of receiver configurations. The trainable logic includes: a determination logic configured to determine a plurality of available receiver configurations and associate each receiver configuration with a context matrix; codebook logic configured to select, for the context matrix, a quantized codebook to be used by the trainable logic; and learning logic configured to learn according to a training data set, the training data set comprising a plurality of received signal samples related to reconstruction of the transmit message; the learning logic is configured to generate from the training data set: a set of overlay parameters and context matrices corresponding to a plurality of available receiver configurations, and a set of context parameters for each context, the context parameters being generated by combining the overlay parameters with the context matrices associated with each receiver configuration; quantizing the context matrix according to a quantization codebook; and repeating the superposition parameter, the generation of the context matrix, and the quantization of the context matrix until a stop criterion is satisfied. Arrangements may recognize that performing context (receiver configuration) switching becomes computationally more efficient by providing context matrices for each receiver configuration and aligning those context matrices with a simple codebook.

Description

technical field [0001] Various example embodiments relate to methods and apparatus that may be used to facilitate selection of one of a plurality of available receiver configurations for demapping received signals at a receiver in a wireless communication network. Background technique [0002] Neural Networks (NN) can be used in communication systems to improve system performance. For example, for a receiver or transceiver within a communication network, a neural network may be trained on input parameters such that for a given system configuration, the neural network selects a desired mode of operation (output parameters). [0003] Neural networks configured to make decisions or identify outcomes based on a set of input samples usually perform well. One of the reasons for the success of NNs is their ability to generalize well when faced with samples not seen at training time but drawn from the distribution from which the training dataset was sampled. [0004] A disadvantag...

AI Technical Summary

Problems solved by technology

Such increased hardware requirements may make methods requiring multiple NNs unpopular in practice

Images