Committee: 

Dr. Romberg, Advisor   

Dr. Raychowdhury, Chair

Dr. Wang

Abstract:

The objective of the proposed research is to combine theory in machine learning, signal processing, and system control for hardware performance optimization. By leveraging collected data to construct a better model for the environment and for specific tasks, machine learning enables the hardware to operate more power-efficiently, to obtain improved results, and to stay robust against environmental changes. The proposed work target three aims: (i) design machine learning algorithms that work with compressively sensed data; (ii) exploit machine learning to improve the speed and the quality of compressive sensing recovery; and (iii) design an adaptive control algorithm for efficient transmitter power amplifier linearization.