Search
Now showing items 31-37 of 37
Learning embodied models of actions from first person video
(Georgia Institute of Technology, 2017-08-28)
Advances in sensor miniaturization, low-power computing, and battery life have enabled the first generation of mainstream wearable cameras. Millions of hours of videos are captured by these devices every year, creating a ...
Innovative mining, processing, and application of big graphs
(Georgia Institute of Technology, 2017-03-22)
With continued advances in science and technology, big graph (or network) data, such as World Wide Web, social networks, academic collaboration networks, transportation networks, telecommunication networks, biological ...
Combining logical and probabilistic reasoning in program analysis
(Georgia Institute of Technology, 2017-08-23)
Software is becoming increasingly pervasive and complex. These trends expose masses of users to unintended software failures and deliberate cyber-attacks. A widely adopted solution to enforce software quality is automated ...
Efficient programming of massive-memory machines
(Georgia Institute of Technology, 2017-08-24)
New and emerging memory technologies combined with enormous growths in data collection and mining within industry are giving rise to servers with massive pools of main memory — terabytes of memory, disaggregated bandwidth ...
Personalized mobile tools to support the cancer trajectory
(Georgia Institute of Technology, 2017-11-13)
When managing cancer, people encounter many physical, emotional, social, and logistical challenges that impede on their quality of life and their ability to effectively manage their health. Helping people overcome these ...
Improving robustness of DNS graph clustering against noise
(Georgia Institute of Technology, 2017-11-22)
Clustering is often the first step performed to assist us in finding structure within unlabeled datasets. Given a small set of labels, clustering also enables us to propagate these labels by discovering groups of objects ...
High performance computing algorithms for discrete optimization
(Georgia Institute of Technology, 2017-11-03)
This thesis concerns the application of High Performance Computing to Discrete Optimization, and the development of massively parallel algorithms designed to accelerate the solving process of Mixed-Integer Programs (MIPs). ...