How can an agent generalize its knowledge to new circumstances? To learn
effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
This thesis considers the problem of training convolutional neural networks for online visual tracking. A major challenge for single object visual tracking is that most training sets with frame-level track annotations are quite small, due to the prohibitive cost of manual annotation. Current training approaches either supplement the annotations with...
Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
This thesis considers the problem in which a teacher is interested in teaching action policies to computer agents for sequential decision making. The vast majority of policy
learning algorithms o er teachers little flexibility in how policies are taught. In particular,
one of two learning modes is typically considered: 1)...
Utilizing Danio rerio (zebrafish) as a model organism has gained popularity recently, however a lack of research into their immune response pathways had led to the discovery of subclinical infections, and has potentially confounded results. We conducted a study to determine the cytokine expression from TLR activation in order to...
Descriptions of the fire regime in the Douglas-fir/western hemlock region of the Pacific Northwest traditionally have emphasized infrequent, predominantly stand-replacement fires and an associated linear pathway of stand development, where all stands proceed along a common pathway until reset by the next fire. Although such a description may apply in...
Advances of colloidal nanomaterials for societal benefit have been hampered by the high cost and low quality of nanoparticles (NPs). The production of high quality nanoparticles within colloidal suspension has two related concerns; (1) current high production rates methods of synthesizing nanoparticles result in a larger range of particle size,...
The following three essays explore the use of the directional output distance function (Chambers et al., 1996), an economic model originally developed to measure efficiency and productivity for multi-input and multi-output production processes, to assess performance for multi-attributed environmental processes.
The first essay illustrates the use of the directional output...
In this study, we contrasted socioemotional selectivity theory (SST;
Carstensen, 2006) with dynamic integration theory (DIT; Labouvie-Vief, 2003) using
trajectories of quantitative and qualitative social support in later life. SST is a lifespan
theory of motivational development (Carstensen, Isaacowitz, & Charles, 1999). There
is a normative decline in social support...