Avian vacuolar myelinopathy (AVM) is a neurologic disease of unknown etiology that affects bald eagles (Haliaeetus leucocephalus), American coots (Fulica americana), and several species of waterfowl. An unidentified neurotoxin is suspected as the cause of AVM, which has been documented at several reservoirs in the southeastern United States. We conducted diagnostic and epidemiologic studies ann...

Diagnostic records of 227 bald eagles (Haliaeetus leucocephalus) and 78 golden eagles (Aquila chrysaetos) collected in Saskatchewan, during 1992 to 2012, were reviewed to identify common causes of mortality. The most frequent cause of death in bald eagles was toxicosis (53%), followed by trauma (22%), electrocution (6%), infectious disease (4%), malnutrition (3%), and idiopathic disease (2%). T...

Automatic problem generation for learning tools can provide the required quantity and variation of problems necessary for an intelligent tutoring system. However, this requires an understanding of problem difficulty and corresponding features of student performance. Our goal is to automatically generate new proof problems in Deep Thought – an online propositional logic learning tool – for indiv...

The Georgia Institute of Technology has been a catalyst for economic growth in the Southeast United States since its founding in 1885. Over the past 30 years, it has become known as one of the top technological universities in the world. As part of a strategic planning effort in mid2009, it sought to strengthen its thought leadership and impact through the implementation of a global innovation ...

Deep Thought is a logic tutor where students practice constructing deductive logic proofs. Within Deep Thought is a data-driven mastery learning system (DDML), which calculates student proficiency based on rule scores weighted by expert-decided weights in order to assign problem sets of appropriate difficulty. In this study, we designed and tested a data-driven proficiency profiler (DDPP) metho...

We describe the “Deep Thought” algorithm, which can, among other things, take a commutator presentation for a finitely generated torsion-free nilpotent group G, and produce explicit polynomials for the multiplication of elements of G. These polynomials were first shown to exist by Philip Hall, and allow for “symbolic collection” in finitely generated nilpotent groups. We discuss various practic...

We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoderdecoder model: in this paper, we consider RNN decoders with both CNN and RNN encoders. The review network performs a number of review steps with attention mechanism on the encoder hidden states, and outputs a thought vector after each review s...

When developing an intelligent tutoring system, it is necessary to have a significant number of highly varied problems that adapt to a student’s individual learning style. In developing an intelligent tutor for logic proof construction, selecting problems for individual students that effectively aid their progress can be difficult, since logic proofs require knowledge of a number of concepts an...

We summarize information available on natural history, numbers, distribution, and status of bald eagles (Haliaeetus leucocephalus) in six regions of interior Alaska: Upper Yukon, Lower Yukon, Tanana, Kuskokwim, Susitna, and Upper Copper. We identified 347 nesting territories using information from local researchers, a raptor nest atlas, unpublished raptor survey reports, and our own surveys. Ne...

BACKGROUND Quantifying individual variability in movement behavior is critical to understanding population-level patterns in animals. Here, we explore intraspecific variation in movement strategies of bald eagles (Haliaeetus leucocephalus) in the north Pacific, where there is high spatiotemporal resource variability. We tracked 28 bald eagles (five immature, 23 adult) using GPS transmitters bet...