A method for decoding a symbol transmitted over a millimeter wave (mmWave) channel estimates channel state information (CSI) of the mmWave channel using a Bayesian inference on a test symbol according to a probabilistic model of the mmWave channel including statistics on paths and spread of mmWaves propagating in the mmWave channel and decodes a symbol received over the mmWave channel using the CSI.

A data channel on an integrated circuit device includes a non-linear equalizer having as inputs digitized samples of signals on the data channel, decoding circuitry configured to determine from outputs of the non-linear equalizer a respective value of each of the signals, and adaptation circuitry configured to adapt parameters of the non-linear equalizer based on respective ones of the value. The non-linear equalizer includes a non-linear filter portion, and a front-end filter portion configured to reduce numbers of the inputs from the digitized samples. The non-linear equalizer may be a neural network equalizer, such as a multi-layer perceptron neural network equalizer, a reduced complexity multi-layer perceptron neural network equalizer, or a radial-basis function neural network equalizer. Alternatively, the non-linear equalizer may include a linear filter and a non-linear activation function, which may be a hyperbolic tangent function.

Adaptive channel aging detection to determine channel sounding intervals in a wireless network is provided. A station may receive data packets from an Access Point (AP) over a channel established between the AP and the station. The station may estimate a channel condition of the channel based on Legacy Long Training Field (L-LTF) symbols in the data packets. The station may determine an amount of variation in the channel condition estimated so far from a latest Channel Sounding Information (CSI) report. The station may determine whether the latest CSI report is still valid based on the variation.

A distributed unit (DU) may include a transceiver configured to communicate with a plurality of radio units (RUs) that are configured to serve a plurality of user equipments (UEs). The DU may include a processor configured to determine RU precoding parameters for UEs served by a first RU set from the plurality of RUs based on estimated channel parameters for communication channels between the first RU set and at least one of interfering UEs served by other RUs from the plurality of RUs; to encode information indicating the determined precoding parameters for downlink transmissions to the first RU set and determine DU precoding parameters for downlink transmissions to the UEs served by the first RU set based on the determined RU precoding parameters; and/or precode communication signals based on the determined DU precoding parameters.

A wireless communication system may use forward-forward learning to for end-to-end learning. A transmitter may pass a positive dataset and a negative dataset through each of its layers for model training. Each layer may correspond to a goodness function. The transmitter may send the positive dataset to a receiver. The receiver may generate a second positive dataset and a second negative dataset based on the positive dataset sent from the receiver. The receiver may train each of its layers using the second positive dataset and the second negative dataset.