The current milieu, encourages rapid growth of wireless communication, multimedia
applications, robotics and graphics to have efficient utilization of resources with high …

Error resilience in neural networks has allowed for the adoption of low-precision floating-
point representations for mixed-precision training to improve efficiency. Although the IEEE …

This paper proposes a set of methods that enables low precision posit™ arithmetic to be
successfully used for the training of generative adversarial networks (GANs) with minimal …

Matrix multiplication is an important operation for many engineering applications.
Sometimes new features that include matrix multiplication should be added to existing and …

This dissertation studies the application of machine learning in the fields of Glaciology and
Paleomagnetism. In the past few years, there have been significant advances in introducing …

Image segmentation is an important topic in computer vision which encompasses a variety
of techniques to divide image into multiple areas or sub-regions in order to extract …

We present a method for randomizing formulas for bilinear computation of matrix products
which does not increase the leading order complexity of the computation. We consider the …

Error resilience in neural networks has allowed for the adoption of low-precision floating-
point representations for mixed-precision training to improve efficiency. Although the IEEE …

This dissertation looks at matrices and tensors from a computational perspective. An
important problem in both matrix and tensor computations is decomposition. Several …