Physical experimentation in various scientific and engineering areas continues to be a useful and often necessary approach that is applied in research, development, and for general problem solving. The experimental design process however, is iterative and often involves trial and error. Alternative designs are proposed and evaluated on cost and...
Collaboration is tricky, but often beneficial in the context of numerous software related activities, from learning core concepts, to the design and implementation of large software products. The growth of online classes, from small structured seminars to massive open online courses (MOOCs), and the isolation and impoverished learning experience some...
In general, making optimal decisions is a never ending challenge that decision makers face. A comprehensive model that integrates decisions at all three levels of decision making (i.e., strategic, tactical, and operational) can help the decision maker to find solutions that best serve the organization's performance. However, as organizations expand...
In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training. To detect unknown classes while still generalizing to new instances of existing classes, this thesis introduces a dataset augmentation technique called counterfactual image generation. This approach, based on...
Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
Analysis of observations on sequential events over time is common in real life. Sequential measurements over time describing the behavior of systems are usually called time series data, which have been collected in a wide range of disciplines. Over the years there have been multiple research areas in studying stochastic...
This dissertation addresses few-shot object segmentation in images. The goal of segmentation is to label every image pixel with a class of the object occupying that pixel, where the class may represent a semantic object category or instance. In few-shot segmentation, training and test datasets have different classes. Every new...