Engineering Commons^™

Extending Structural Learning Paradigms For High-Dimensional Machine Learning And Analysis, Christopher Todd Symons

Doctoral Dissertations

Structure-based machine-learning techniques are frequently used in extensions of supervised learning, such as active, semi-supervised, multi-modal, and multi-task learning. A common step in many successful methods is a structure-discovery process that is made possible through the addition of new information, which can be user feedback, unlabeled data, data from similar tasks, alternate views of the problem, etc. Learning paradigms developed in the above-mentioned fields have led to some extremely flexible, scalable, and successful multivariate analysis approaches. This success and flexibility offer opportunities to expand the use of machine learning paradigms to more complex analyses. In particular, while information is often …

Hard And Soft Error Resilience For One-Sided Dense Linear Algebra Algorithms, Peng Du

Doctoral Dissertations

Dense matrix factorizations, such as LU, Cholesky and QR, are widely used by scientific applications that require solving systems of linear equations, eigenvalues and linear least squares problems. Such computations are normally carried out on supercomputers, whose ever-growing scale induces a fast decline of the Mean Time To Failure (MTTF). This dissertation develops fault tolerance algorithms for one-sided dense matrix factorizations, which handles Both hard and soft errors.

For hard errors, we propose methods based on diskless checkpointing and Algorithm Based Fault Tolerance (ABFT) to provide full matrix protection, including the left and right factor that are normally seen in …

Meal Helper, Jacob Taylor Peek, David Prenshaw, Matthew Burnett, Ian Harmon

Chancellor’s Honors Program Projects

No abstract provided.

Deep Machine Learning With Spatio-Temporal Inference, Thomas Paul Karnowski

Doctoral Dissertations

Deep Machine Learning (DML) refers to methods which utilize hierarchies of more than one or two layers of computational elements to achieve learning. DML may draw upon biomemetic models, or may be simply biologically-inspired. Regardless, these architectures seek to employ hierarchical processing as means of mimicking the ability of the human brain to process a myriad of sensory data and make meaningful decisions based on this data. In this dissertation we present a novel DML architecture which is biologically-inspired in that (1) all processing is performed hierarchically; (2) all processing units are identical; and (3) processing captures both spatial and …

A Framework For Federated Two-Factor Authentication Enabling Cost-Effective Secure Access To Distributed Cyberinfrastructure, Matthew Allan Ezell

Masters Theses

As cyber attacks become increasingly sophisticated, the security measures used to mitigate the risks must also increase in sophistication. One time password (OTP) systems provide strong authentication because security credentials are not reusable, thus thwarting credential replay attacks. The credential changes regularly, making brute-force attacks significantly more difficult. In high performance computing, end users may require access to resources housed at several different service provider locations. The ability to share a strong token between multiple computing resources reduces cost and complexity.

The National Science Foundation (NSF) Extreme Science and Engineering Discovery Environment (XSEDE) provides access to digital resources, including supercomputers, …