This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
Oregon's estuaries are important ecosystems for scientific study. Consequently, knowledge of what research has been conducted helps us identify benchmarks and plan new projects. A comprehensive bibliography of published research, technical reports, local documents, and data sets is one means of recording this knowledge. For these reasons, the Guin Library...
The utility of high-throughput, computational screening has become an invaluable asset to the field of materials science. In the hierarchy of computational methods, the most accurate methods are often the most computationally expensive. However, as both the efficiency and fidelity of numerical techniques advance, high-quality screening of large materials datasets...
Multiagent approaches are well suited to designing autonomous solutions for systems that feature complex interactions between many individuals such as in autonomous traffic systems and multi-robot exploration systems. However, creating autonomous agents that function effectively in these systems is a challenging task. In these complex environments, agents need informative reward...
Ice–ocean interactions have profound consequences for the ocean and climate, influencing the rate of sea level rise. Submarine melt is commonly parameterized using a three-equation formulation for the heat, salt, and momentum conservation equations coupled to a buoyant plume model, together called plume-melt theory. However, recent direct observations of terminus...
Toxin production by cyanobacterial harmful algal blooms (cyanoHABs) in freshwater systems has lasting ecological and human impacts. Nutrients, light availability, hydrology, and microbial community composition impact the frequency and intensity of toxic cyanoHABs. Climate change will exacerbate toxic cyanoHABs, making real time and predictive monitoring a vital tool for managing...
Basin-scale superinertial oceanic tides have been observed globally to resonate with the continental shelf (e.g., the Patagonian Shelf) with a clear theoretical framework. However, the response of the shelf to atmospheric tides – another basin-scale forcing – has not been discussed. This study explores this response using a prominent S2...
The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
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...