Abstract: Apparatuses, systems, and techniques to generate images. In at least one embodiment, one or more machine learning models generate an output image based, at least in part, on calculating attention scores using time embeddings.

Abstract: Methods and systems are described for training a machine learning (ML) model to predict the gain of a target channel of a multi-channel amplifier device. An ML model may be pre-trained using an existing set of training objects. The trained ML model then can be utilized to suggest further useful training objects to be labelled that will improve the performance of the ML model by predicting more accurate target channel gains given the on/off value for the channel inputs.

Abstract: Multi-user pairing of a plurality of wireless devices refers to the selection of different devices for simultaneously sharing a frequency band during a shared time interval. A method for performing wireless multi-user pairing of a plurality of user equipment (UE) is performed using a neural network model for a wireless communication network. The method includes: receiving channel state information (CSI) between each UE of a plurality of UEs and a base station with a plurality of antennas in the wireless communication network; converting the UE CSIs to an input sequence; and inputting the input sequence to system implementing the neural network model, the neural network model configured to generate pairing information for each UE based on the input sequence, the pairing information for each UE indicative of whether the UE is to share a frequency resource during a shared time interval.

Abstract: Multi-user pairing of a plurality of wireless devices refers to the selection of different devices for simultaneously sharing a frequency band during a shared time interval. A method for performing wireless multi-user pairing of a plurality of user equipment (UE) is performed using a neural network model for a wireless communication network. The method includes: receiving channel state information (CSI) between each UE of a plurality of UEs and a base station with a plurality of antennas in the wireless communication network; converting the UE CSIs to an input sequence; and inputting the input sequence to system implementing the neural network model, the neural network model configured to generate pairing information for each UE based on the input sequence, the pairing information for each UE indicative of whether the UE is to share a frequency resource during a shared time interval.

Abstract: Methods and systems are described for training a machine learning (ML) model to predict the gain of a target channel of a multi-channel amplifier device. An ML model may be pre-trained using an existing set of training objects. The trained ML model then can be utilized to suggest further useful training objects to be labelled that will improve the performance of the ML model by predicting more accurate target channel gains given the on/off value for the channel inputs.