Search

Now showing items 1-6 of 6

Graphical Models with Structured Factors, Neural Factors, and Approximation-aware Training

Gormley, Matthew R. (Johns Hopkins University, 2015-10-23)

This thesis broadens the space of rich yet practical models for structured prediction. We introduce a general framework for modeling with four ingredients: (1) latent variables, (2) structural constraints, (3) learned ...

Topic Modeling with Structured Priors for Text-Driven Science

Paul, Michael John (Johns Hopkins University, 2015-07-24)

Many scientific disciplines are being revolutionized by the explosion of public data on the web and social media, particularly in health and social sciences. For instance, by analyzing social media messages, we can instantly ...

Securing Medical Devices and Protecting Patient Privacy in the Technological Age of Healthcare

Martin, Paul D (Johns Hopkins University, 2016-02-18)

The healthcare industry has been adopting technology at an astonishing rate. This technology has served to increase the efficiency and decrease the cost of healthcare around the country. While technological adoption has ...

Modeling the Representation of Medial Axis Structure in Human Ventral Pathway Cortex

Tokgozoglu, Haluk Noyan (Johns Hopkins University, 2016-07-21)

Computational modeling of the human brain has long been an important goal of scientific research. The visual system is of particular interest because it is one of the primary modalities by which we understand the world. ...

Using Machine Learning to Study the Relationship Between Galaxy Morphology and Evolution

Peth, Michael Andrew (Johns Hopkins University, 2016-07-05)

We can track the physical evolution of massive galaxies over time by characterizing the morphological signatures inherent to different mechanisms of galactic assembly. Structural studies rely on a small set of measurements ...

THE SPATIAL INDUCTIVE BIAS OF DEEP LEARNING

Mitchell, Benjamin R. (Johns Hopkins University, 2017-03-17)

In the past few years, Deep Learning has become the method of choice for producing state-of-the-art results on machine learning problems involving images, text, and speech. The explosion of interest in these techniques ...