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...
New capabilities in wireless network security are now possible through deep learning, which can identify and leverage patterns in radio frequency (RF) data. One area of deep learning, known as open set detection, is focused on detecting data instances from new devices encountered during deployment that were not previously seen...
Compositional data is a type of data where the features are non-negative and always sum to a constant. This type of data is frequently encountered in many fields such as microbiology, geology, economics and natural language processing. Compositional data has unique statistical properties that makes it difficult to apply standard...
Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...