This dissertation focuses on indoor free-space optical communications systems for use in short range wireless networks. We propose that current radio frequency wireless links be augmented or replaced with optical frequency links due to overcrowding in the radio frequency spectrum. Optical frequencies contain hundreds of terahertz of unregulated bandwidth and...
This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...