Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"hypersphere"”.
-
Machine learning methods based on diffusion processes
… First, the idea of using heat diffusion on a hypersphere to measure similarity has been previously proposed and tested by computer scientists, demonstrating promising results based on a heuristic heat kernel obtained from the zeroth order parametrix expansion; however, how well this heuristic …
-
Unsupervised methods for speaker diarization
… distribution for clustering on a unit hypersphere. Our extended system performs competitively on the diarization of conversations involving two or more speakers. Finally, we present promising initial results obtained from applying variational inference on our front-end speaker …
-
Optimal experimental designs for estimating the slope of a response surface
… is a hypercube and the case in which it is a hypersphere. For the bias component it is found that the optimal designs are rotatable designs regardless of whether the region of interest is a hypercube or a hypersphere. Because the optimal designs are not uniquely determined with respect to the …
-
The quaternion Bingham Distribution, 3D object detection, and dynamic manipulation
… distribution on the 4-D unit quaternion hypersphere. In this thesis, we apply the quaternion Bingham to two applications: 3-D object instance detection from RGB-D images, and robot ping pong. The Bingham enables our object detection system to achieve state-of-the-art detection rates in …
-
Dynamics of Gradient Flow with Contrastive Learning
… collapses to a distinct vertex of a simplex on a hypersphere during training. This property, also seen in other types of learning tasks, might explain why CL works as well as it does. Having class collapse on the test distribution, which determines how well the model generalizes to new samples and …
-
Probabilistic Modelling in Function Space
… in-depth analysis of Gaussian processes on the hypersphere, an idea inspired by infinite-width neural networks. This leads to a class of kernels, known as zonal kernels, and a linear-time Gaussian process method that address the scalability concerns. Building on this, the second contribution …
-
Motor Imagery Based Brain Computer Interfaces
… are generated by linearly transforming the hypersphere into an N dimensional ellipsoid using singular value decomposition (SVD). A number of experiments on synthetic and real-world signals were conducted to show that the non-uniform sampling scheme is helpful to generate meaningful IMFs when …
-
On the Efficiency of Designs for Linear Models in Non-regular Regions and the Use of Standard Desings for Generalized Linear Models
… that is either a p-dimensional hypercube or hypersphere and any point inside or on the boundary of the shape is a candidate design point. However, some economic, or practical constraints may occur that restrict factor settings and result in an irregular experimental region. For the two- and …
-
Learning and Exploiting Camera Geometry for Computer Vision
… space, and the Bingham distribution on the unit hypersphere. It is shown to inherit many of the convenient properties of these special cases: it is the maximum-entropy distribution with fixed second moment, and there is a generalized Laplace approximation whose result is the mirrored …
-
Graphical assessment of the prediction capability of response surface designs
… of prediction at locations on the surface of a hypersphere are presented in this thesis. These measures are used to form a graphical method of assessing the overall prediction capability of an experimental design throughout the region of interest. Rotatable designs give equal variances of …
-
Towards a Fast and Accurate Face Recognition System from Deep Representations
… descriptors which restricts them to lie on a hypersphere of a fixed radius. This module can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly boosts the performance of face verification. We …
-
Electrostatically-driven self-assembly of polyelectrolytes and colloidal tetrapods
I present research in the aggregation and self-assembly of charged macromolecules. This work aligns along three themes. The first theme is the effective interactions and aggregation of rodlike polyelectrolytes. The second theme is the self-assembly of colloidal tetrapods using Monte Carlo …