Search
Now showing items 21-30 of 98
On internal language representations in deep learning : an analysis of machine translation and speech recognition
(Massachusetts Institute of Technology, 2018)
Language technology has become pervasive in everyday life. Neural networks are a key component in this technology thanks to their ability to model large amounts of data. Contrary to traditional systems, models based on ...
Faster linear algebra for data analysis and machine learning
(Massachusetts Institute of Technology, 2018)
We study fast algorithms for linear algebraic problems that are ubiquitous in data analysis and machine learning. Examples include singular value decomposition and low-rank approximation, several varieties of linear ...
A scalable quantum computation platform : solid state quantum memories coupled to photonic integrated circuits
(Massachusetts Institute of Technology, 2018)
Quantum computation and communication systems exploit quantum mechanical effects to surpass their classical counterparts in certain applications. However, while proof-of-principle experimental demonstrations have been ...
Cryptography for societal benefit
(Massachusetts Institute of Technology, 2018)
The deployment of cryptography in society has a range of effects that are not always evident when studying cryptography as a technological construct in isolation. This observation suggests a number of natural research ...
Improving clinical decisions using correspondences within and across electronic health records
(Massachusetts Institute of Technology, 2018)
Electronic Health Record (EHR) adoption and retrospective analyses of health care data are part of a broader conversation about health care quality and cost in the United States. Machine learning in health care can be used ...
Sparse approximations, iterative methods, and faster algorithms for matrices and graphs
(Massachusetts Institute of Technology, 2018)
This thesis aims to advance our algorithmic understanding of some of the most fundamental objects in computer science: graphs and matrices. Specifically, on one hand, we develop a broad set of sampling techniques that yield ...
Co-design of on-chip caches and networks for scalable shared-memory many-core CMPs
(Massachusetts Institute of Technology, 2018)
Chip Multi-Processors(CMPs) have become mainstream in recent years, providing increased parallelism as core counts scale. While a tiled CMP is widely accepted to be a scalable architecture for the many-core era, on-chip ...
Analyzing and synthesizing deformations in image datasets
(Massachusetts Institute of Technology, 2018)
Many tasks in computer vision and graphics, such as image registration, optical flow estimation and image warping, are concerned with measuring spatial deformations between images. Traditional algorithms for these applications ...
3D-printing form and function
(Massachusetts Institute of Technology, 2018)
Integrating diverse functions inside man-made parts with specific shapes, in a highly scalable manner, is the central challenge in manufacturing. Functional integration is typically achieved by assembling specialized parts, ...
Integrated silicon photonic circuit simulation
(Massachusetts Institute of Technology, 2018)
Integrated silicon photonics is an exciting emerging technology, utilizing the high bandwidth and high timing resolution that optics provides in many applications. To maximize the benefits of these optical-electrical ...