Engineering Commons^™

The L1-Norm Regularized L1-Norm Best-Fit Line Problem And Applications, Xiao Ling

Theses and Dissertations

The best-fit subspace or low-rank approximation of a data matrix revolves
around the norm approximation technique. l²-norm criterion is probably the most
widely used norm for fitting subspaces. As the computational power increases, the
l¹-norm analogue has recently gained attention from the academic community. It is
widely agreed that the l¹ norm is insensitive to outliers, compared to its l² variant.
Because of the polyhedral structure interrelated with linear programming (LP),
the l⁰ norm is commonly relaxed into the l¹-norm problem to induce sparsity in
models. In this work, we examine …

Cadent Diffusion: Permeating The Membrane, Isabella M. Kubo

Theses and Dissertations

cadent diffusion: permeating the membrane explores and documents KUBO's journey of cultivating a sustainable and curious artistic practice during their Master’s program in Richmond, Virginia (Powhatan Land) from the Fall of 2020 to the Spring of 2022.

KUBO's practice is the affirmation between life and change in an attempt to work along the forces of singularity; to free lines, scores, concepts, and events from structures that otherwise bind them.The cadent diffusion is the rhythm in this force. Or perhaps, it is the force itself.

Learning Robot Motion From Creative Human Demonstration, Charles C. Dietzel

Theses and Dissertations

This thesis presents a learning from demonstration framework that enables a robot to learn and perform creative motions from human demonstrations in real-time. In order to satisfy all of the functional requirements for the framework, the developed technique is comprised of two modular components, which integrate together to provide the desired functionality. The first component, called Dancing from Demonstration (DfD), is a kinesthetic learning from demonstration technique. This technique is capable of playing back newly learned motions in real-time, as well as combining multiple learned motions together in a configurable way, either to reduce trajectory error or to generate entirely …