In weak supervision learning, label information can be provided at different levels of granularity. For example, in multi-instance multi-label learning, samples are organized into bags and labels for each class are provided at the bag level. For small datasets, this approach offers means of reducing the labeling efforts. However, in...
Deep learning is becoming the latest trend in sensitive applications, such as healthcare, criminal justice, and finance. As these new applications emerge, adversaries are circumventing them.
Further, there have been concerns about the possibility of bias and discrimination in predictive applications.
In order to address these issues, we propose an...
How can software practitioners assess whether their software supports diverse users? Although there are empirical processes that can be used to find “inclusivity bugs” piecemeal, what is often needed is a systematic inspection method to assess software’s support for diverse populations. To help fill this gap, this thesis introduces InclusiveMag,...
...................................................... 83
Appendix C: Documents from the Multi-Case Study Teams ..................................... 84
The objective of this dissertation is to enhance the monitoring of forest ecosystems through the utilization of remotely sensed data to address the exigencies posed by the Anthropocene. On a global scale, rising temperatures and fluctuating precipitation patterns have strained forests and produced shifts in natural disturbance regimes. Additionally, the...
Meta-methodologies have been created to assist systems thinking practitioners in selecting applicable intervention approaches for different system states; however, current meta-methodologies do not address the lack of accessibility for non-systems thinking practitioners. To address this problem, the key system states that contribute the most to reduce the variety gap between...
The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
Gall-associated phytopathogens have unique evolutionary histories that haveshaped both their modes of infection and genomic structures. Pathogenicity of the gall-associated plant pathogens of the Rhodococcus, Agrobacterium, and Rathayibactergenera is mediated by horizontally acquired virulence loci. The relative ease of gainand loss of the virulence loci has confounded accurate characterization of...
In the first set of studies, 2 experiments evaluated the influence of supplement composition on ruminal forage disappearance, performance, and physiological responses of Angus × Hereford cattle consuming a low-quality, cool-season forage (8.7 % CP and 57 % TDN). In Exp. 1, 6 rumen-fistulated steers housed in individual pens were...