Cognitively adaptable front-end with FPNA enabled integrated network executive
AssigneeRockwell Collins, Inc.
InventorsOrion Davies, Russell D. Wyse
Life of this patent
Estimating the term…
Abstract
A system-in-package or multi-chip module architecture that includes a field programmable neural array, that instantiates an instance of a neural network model trained to receive internal observation signals from a digitally controlled integrated circuit, and rapidly generate corresponding system settings to optimize desired characteristics. The system continuously adapts system settings to environmental conditions via a feedback loop of observation signals. The field programmable neural array may also receive observation signals external to the module to generate system settings based on factors not otherwise definable by internal signal characteristics.
Claims20
A System-in-Package (SiP) or Multi-Chip-Module (MCM) integrated circuit architecture comprising:
- a digitally controlled ultra-wideband receiver;
- a digitally reconfigurable filtering element;
- and
- a field programmable neural array that houses an instance of a trained neural network model to:
- continuously receive internal observation signals defined by the ultra-wideband receiver and the reconfigurable filtering element;
- process the internal observation signals to determine one or more action signals to apply settings to the receiver and reconfigurable filtering element;
- and
- directly apply the action signals as digital inputs to reconfigure the receiver and reconfigurable filtering element.
A system-in-package or multi-chip module comprising:
- an ultra-wideband receiver;
- a reconfigurable filtering element;
- and
- a field programmable neural array trained to:
- continuously receive internal observation signals defined by the ultra-wideband receiver and the reconfigurable filtering element;
- process the internal observation signals to determine one or more action signals to apply settings to the receiver and reconfigurable filtering element;
- and
- directly apply the action signals to reconfigure the receiver and reconfigurable filtering element.
A radio comprising:
- an ultra-wideband receiver;
- a reconfigurable filtering element;
- and
- a field programmable neural array that houses an instance of a trained neural network model to:
- continuously receive internal observation signals defined by the ultra-wideband receiver and the reconfigurable filtering element;
- process the internal observation signals to determine one or more action signals to apply settings to the receiver and reconfigurable filtering element;
- and
- directly apply the action signals to reconfigure the receiver and reconfigurable filtering element.
Dependencies are inferred from the claim text.