In real-world applications, the environment in which a machine learning system is deployed tends to change due to many factors, such as sample selection bias, prior probability mismatch, and domain shift. This makes it ...

In the big data era, most of the data generated every day are high dimensional such as text and image data. Learning compact representations from the input data can help in dealing with the high dimensionality and visualization ...

In Sudan, practices of agroforestry once created closed-loop cycles of production that harmoniously linked landscape, agriculture, craft, and architecture. However, these practices have largely been wiped out by past ...

Recently, one of the more significant measures on the part of the Cuban government to enhance resiliency of the existing economy was the announcement of a series of economic and social policy proposals referred to as ...

This thesis explores the central research question: how are lessons learned from experiences with disasters? Based on three case studies detailing Nova Scotia Emergency Management Office’s experiences responding to the ...

Adding small perturbations to test images can drastically change the classification accuracy of machine learning models. These perturbed examples are called adversarial examples (Szegedy et al., 2013). Studying these ...

Early motor learning is driven by error commission and feedback during physical practice (PP). Motor learning can also be facilitated by action observation (AO), which classically involves observing a skilled model flawlessly ...

Every year, up to 1.4 million shorebirds, such as the Semipalmated Sandpiper (Calidris pusilla), use the Bay of Fundy and the Minas Basin as a stopover site before continuing their transoceanic migration to their southern ...