Search
Now showing items 1-10 of 283
Implementation of a cross-platform automated Bayesian data modeling system
(Massachusetts Institute of Technology, 2020)
Understanding the underlying structure of a high-dimensional dataset is a quintessential task in data science and multivariate statistics. The CrossCat model class provides an automated solution by using Bayesian Non-Parametric ...
A Counting : system architecture and implementation of a voice portrait of the United States
(Massachusetts Institute of Technology, 2020)
In this thesis, I present the technical architecture of A Counting, a voice portrait of the United States through a nationwide repeating "count" from one to one hundred as a response to historical miscounting by the US ...
Modular graph-structured models for prediction and control
(Massachusetts Institute of Technology, 2020)
In contrast to models that assume no structural prior about the system being modelled, structured models requires far less computational resources to train and are more interpretable by nature of their modularity. In this ...
Testing certified control for LIDAR and vision perception via physical testing and simulation
(Massachusetts Institute of Technology, 2020)
Certified control is a proposed safety architecture for autonomous vehicles. It consists of a runtime monitor that requires evidence from the vehicle's main controller to prove that the controller's desired action is safe. ...
New methods for studying old work
(Massachusetts Institute of Technology, 2020)
Understanding the task content of new jobs is crucial to understanding labor markets. However, structured, task-level data about jobs in the US is nonexistent for the earlier decades of the 20th century. In this thesis, I ...
Back-end design and development of a energy systems analysis tool
(Massachusetts Institute of Technology, 2020)
Sustainable Energy System Analysis Modeling Environment (SESAME) is a modular analytic environment designed for supporting various pathway-level and system-level analyses [1]. Pathway, in this context, refers to life cycle ...
Toward robust deep stereo networks : uncertainty learning, novelty detection, and online adaptation
(Massachusetts Institute of Technology, 2020)
Although deep learning continues to improve the state-of-the-art for stereo depth estimation on benchmark computer vision datasets, there are many remaining challenges in making these algorithms robust enough for deployment ...
Pipelines for deep contextual patient-level clinical outcome prediction
(Massachusetts Institute of Technology, 2020)
Longitudinal health data provides a uniquely detailed view into the evolution of patient health over time. We develop pipelines to efficiently work with this kind of data in its rawest form, enabling the development of new ...
A machine learning automation system for utilization management
(Massachusetts Institute of Technology, 2020)
We develop high-performance machine learning automation systems for utilization management that are effective across all specialties. We were motivated by the knowledge that current automation systems for utilization ...
A step toward dynamic displays and ecological data collection In cognitive testing
(Massachusetts Institute of Technology, 2020)
We have a developed a proof-of-concept for a testing ecosystem for cognitive disorders. This system assists in detection of cognitive disorders by re-implementing existing neurocognitive tests as applications on devices ...