Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: A network control and rate optimization solution for multiuser multiple input multiple output (MU-MIMO) communications in wireless networks. This solution is decentralized and includes scheduling and routing of the MU-MIMO communication links that adapt to dynamic channel, interference, and traffic conditions. The ergodic sum rates of MIMO multiple access channel (MAC) and interference channel (IC) configurations are analyzed by considering the error, and overhead effects due to channel estimation (training) and quantization (feedback). By taking practical considerations such as channel estimation, quantization error and in-network interference into account, the rate gain is shown with an increasing number of antennas compared with single-input single-output (SISO) systems. A distributed channel access protocol to select and activate MU-MIMO configurations is presented with the maximum achievable sum rates using local information on channel, interference, and traffic conditions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels.

Abstract: Methods and systems for dynamic spectrum access (DSA) in a wireless network are provided. A DSA-enabled device may sense spectrum use in a region and, based on the detected spectrum use, select one or more communication channels for use. The devices also may detect one or more other DSA-enabled devices with which they can form DSA networks. A DSA network may monitor spectrum use by cooperative and non-cooperative devices, to dynamically select one or more channels to use for communication while avoiding or reducing interference with other devices.

Abstract: Methods and systems for dynamic spectrum access (DSA) in a wireless network are provided. A DSA-enabled device may sense spectrum use in a region and, based on the detected spectrum use, select one or more communication channels for use. The devices also may detect one or more other DSA-enabled devices with which they can form DSA networks. A DSA network may monitor spectrum use by cooperative and non-cooperative devices, to dynamically select one or more channels to use for communication while avoiding or reducing interference with other devices. A man-made noise rejection sub-system is used to permit signal detection while maintaining a low false alarm rate.

Abstract: Methods and systems for dynamic spectrum access (DSA) in a wireless network are provided. A DSA-enabled device may sense spectrum use in a region and, based on the detected spectrum use, select one or more communication channels for use. The devices also may detect one or more other DSA-enabled devices with which they can form DSA networks. A DSA network may monitor spectrum use by cooperative and non-cooperative devices, to dynamically select one or more channels to use for communication while avoiding or reducing interference with other devices.