This thesis work addresses the creation and evaluation of deep learning architectures which are trained only on synthetic images. The goal of these models is to autonomously detect rocks on the surface of asteroids.
In this paper, we propose a two-stage approach for predicting a trips destination by clustering geocoordinates and leveraging incremental learning and contextual rule-based methods for the prediction of end destinations. The proposed approach dynamically adapts to users change in behavior and is resilient against concept drift. Using this solution, 76.39%...
This is an attempt to recreate a reference architecture with the intention of completing a data engineering capstone project and also learning the services and technologies along the progress. The objective of the project is to use aws cloud managed services to build at scale solution to process, parse and...
With a glut of competing priorities, the financial industry faces major challenges in extracting timely, relevant, and specifically-focused information from text. Without clear-cut business cases, making the investment in text analysis methods does not justify the return on investment. Furthermore, the business landscape continues to become increasingly complex, and at...
Image colorization is the process of artificially coloring a black and white image such that this fabrication appears realistic and authentic to the viewer. There are many nontrivial applications of this process, such as the colorization and augmentation of historical photos as well as the removal of color tone filters...
The ability of a machine to synthesize textual output in a form of human language is a long-standing goal in a field of artificial intelligence and has wide-range of applications such as spell correction, speech recognition, machine translation, abstractive summarization, etc. The statistical approach to enable such ability mainly involves...
In this dissertation, we start with the dictionary learning (DL) based single-frame super-resolution (SR) problem, where low resolution (LR) input frames are super-resolved to high resolution (HR) output frames. We propose to extend the previous single-frame SR methods to multiple-frames, i.e., estimating single HR output frame by multiple LR input...
The goal of this thesis is to design practical algorithms for nonlinear optimization in the case when the objective function is stochastic or nonsmooth. The thesis is divided into three chapters. Chapter 1 describes an active-set method for the minimization of an objective function that is structurally nonsmooth, viz., it...
Thermal overheating is a serious concern in modern supercomputing systems. Elevated temperature levels reduce the reliability and the lifetime of the underlying hardware and increase their power consumption. Previous studies on mitigating thermal hotspots at the hardware and run-time system levels have typically used approaches that trade off performance for...
The task of classification has been increasingly attracting attention from researchers in recent years. The objective is to assign labels given attributes of samples. The classification task is practical in real-world applications and is widely explored in fields such as computer vision, natural language processing and information retrieval. The recent...