CSI Feedback

AI for CSI feedback enhancements

These examples demonstrate AI techniques to process downlink channel state information (CSI).

Featured Examples

New
Prepare Data for CSI Processing

Prepare Data for CSI Processing

Generate channel estimates and prepare a data set to train an autoencoder for channel state information (CSI) feedback compression.

(Communications Toolbox)

  • Since R2025a
CSI Feedback with Transformer Autoencoder

CSI Feedback with Transformer Autoencoder

Design and train a convolutional transformer deep neural network for channel state information feedback by using a downlink clustered delay line (CDL) channel model.

(Communications Toolbox)

  • Since R2024b
CSI Feedback with Autoencoders

CSI Feedback with Autoencoders

Compress downlink channel state information (CSI) for 5G systems by using an autoencoder neural network.

(Communications Toolbox)

  • Since R2022b
Optimize CSI Feedback Autoencoder Training Using MATLAB Parallel Server and Experiment Manager

Optimize CSI Feedback Autoencoder Training Using MATLAB Parallel Server and Experiment Manager

Accelerate determination of the optimal training hyperparameters for a channel state information (CSI) autoencoder by using a Cloud Center cluster and Experiment Manager.

(Communications Toolbox)

  • Since R2024a
NR PDSCH Throughput Using Channel State Information Feedback

NR PDSCH Throughput Using Channel State Information Feedback

Measure the PDSCH throughput of a 5G NR adaptive link that adjusts the MCS, precoding matrix, and number of layers based on the CSI feedback.

(5G Toolbox)