Browsing ETD -- Doctoral Dissertations by Subject "Machine Learning"
Now showing items 1-13 of 13
-
A Semi-Autonomous Neuroprosthesis using Probabilistic Time-Series Inference
(Johns Hopkins UniversityUSA, 2017-01-24)Upper limb neuroprosthesis is a rapidly progressing technology with the potential to restore function to victims of severe paralysis by enabling users to control robotic systems with their neural signals. Great strides ... -
Adaptive Asynchronous Control and Consistency in Distributed Data Exploration Systems
(Johns Hopkins UniversityUSA, 2017-08-29)Advances in machine learning and streaming systems provide a backbone to transform vast arrays of raw data into valuable information. Leveraging distributed execution, analysis engines can process this information effectively ... -
Advances in Systems Science using Network Theory and Machine Learning
(Johns Hopkins UniversityUSA, 2019-02-01)Systems science is widely used for population, public health, traffic, hazard, and other scientific research. New challenges have come up regarding access to big data as well a deeper consideration of systems complexity. ... -
Compute Faster and Learn Better: Model-based Nonconvex Optimization for Machine Learning
(Johns Hopkins UniversityUSA, 2016-12-14)Nonconvex optimization naturally arises in many machine learning problems. Machine learning researchers exploit various nonconvex formulations to gain modeling flexibility, estimation robustness, adaptivity, and computational ... -
Five Tales of Random Forest Regression
(Johns Hopkins UniversityUSA, 2016-10-03)We present a set of variations on the theme of Random Forest regression: two applications to the problem of estimating galactic distances based on photometry which produce results comparable to or better than all other ... -
Generalized Linear Splitting Rules in Decision Forests
(Johns Hopkins UniversityUSA, 2018-03-12)Random forests (RFs) is one of the most widely employed machine learning algorithms for general classification tasks due to its speed, ease-of-use, and excellent empirical performance. Recent large-scale comparisons of ... -
Geometric Deep Learning for Monocular Object Orientation Estimation
(Johns Hopkins UniversityUSA, 2019-01-03)Monocular object orientation estimation or estimating the 3D orientation of an object given a single 2D image of the object, is an important component of traditional computer vision problems like scene understanding and ... -
Heterogeneous Chip Multiprocessor: Data Representation, Mixed-Signal Processing Tiles, and System Design
(Johns Hopkins UniversityUSA, 2019-02-01)With the emergence of big data, the need for more computationally intensive processors that can handle the increased processing demand has risen. Conventional computing paradigms based on the Von Neumann model that separates ... -
Image-set, Temporal and Spatiotemporal Representations of Videos for Recognizing, Localizing and Quantifying Actions
(Johns Hopkins University, 2018-07)This dissertation addresses the problem of learning video representations, which is defined here as transforming the video so that its essential structure is made more visible or accessible for action recognition and ... -
MACHINE LEARNING AND OPTIMIZATION FOR HEALTHCARE AND ENERGY SYSTEMS
(Johns Hopkins UniversityUSA, 2018-05-11)Healthcare and energy systems provide critical service to our society. Recent advancement in information technology has enabled these systems to keep retrieving and storing data. In this dissertation, we used machine ... -
Robust Learning Architectures for Perceiving Object Semantics and Geometry
(Johns Hopkins UniversityUSA, 2018-04-11)Parsing object semantics and geometry in a scene is one core task in visual understanding. This includes classification of object identity and category, localizing and segmenting an object from cluttered background, ... -
Shape Theoretic and Machine Learning Based Methods for Automatic Clustering and Classification of Cardiomyocytes Based on Action Potential Morphology
(Johns Hopkins UniversityUSA, 2017-10-27)Stem cells have been a hot topic in the cardiology community for the last decade and a half. Ever since we learned how to differentiate cardiomyocytes from embryonic and induced pluripotent stem cells, there has been a ... -
Systems Toxicology: Beyond Animal Models
(Johns Hopkins University, 2014-10-16)Toxicology – much like the rest of biology – is undergoing a profound change as new technologies begin to offer a more systems oriented view of cellular physiology. For toxicology in particular, this means moving away ...