Thesis (M.S.)--University of Texas at El Paso, 2009. / Title from title screen. Vita. CD-ROM. Includes bibliographical references. Also available online.

Report (M.S.)--Virginia Polytechnic Institute and State University, 1993. / Abstract. Includes bibliographical references (leaves 55-56). Also available via the Internet.

Thesis--University of Florida. / Description based on print version record. Typescript. Vita. Includes bibliographical references (leaves 46-49).

Thesis (Ph.D.) -- McMaster University, 2000. / Includes bibliographical references (leaves 141-147). Also available via World Wide Web.

Report (M.S.)--Virginia Polytechnic Institute and State University, 1994. / Vita. Abstract. Includes bibliographical references (leaf 59). Also available via the Internet.

This thesis concentrates on the derivation of a modularised version of the DMOS distributed garbage collection algorithm and the implementation of this algorithm in a distributed computational environment. DMOS appears to exhibit a unique combination of attractive characteristics for a distributed garbage collector but the original algorithm is known to contain a bug and, previous to this work, lacks a satisfactory, understandable implementation. The relationship between distributed termination detection algorithms and distributed garbage collectors is central to this thesis. A modularised DMOS algorithm is developed using a previously published distributed garbage collector derivation methodology that centres on mapping centralised collection schemes to distributed termination detection algorithms. In examining the utility and suitability of the derivation methodology, a family of six distributed collectors is developed and an extension to the methodology is presented. The research work described in this thesis incorporates the definition and implementation of a distributed computational environment based on the ProcessBase language and a generic definition of a previously unimplemented distributed termination detection algorithm called Task Balancing. The role of distributed termination detection in the DMOS collection mechanisms is defined through a process of step-wise refinement. The implementation of the collector is achieved in two stages; the first stage defines the implementation of two distributed termination mappings with the Task Balancing algorithm; the second stage defines the DMOS collection mechanisms.

Large-scale heterogeneous distributed computing environments (such as Computational Grids and Clouds) offer the promise of access to a vast amount of computing resources at a relatively low cost. In order to ease the application development and deployment on such complex environments, high-level parallel programming languages exist that need to be supported by sophisticated runtime systems. One of the main problems that these runtime systems need to address is dynamic load balancing that ensures that no resources in the environment are underutilised or overloaded with work. This thesis deals with the problem of obtaining good speedups for irregular applications on heterogeneous distributed computing environments. It focuses on workstealing techniques that can be used for load balancing during the execution of irregular applications. It specifically addresses two problems that arise during work-stealing: where thieves should look for work during the application execution and how victims should respond to steal attempts. In particular, we describe and implement a new Feudal Stealing algorithm and also we describe and implement new granularity-driven task selection policies in the SCALES simulator, which is a work-stealing simulator developed for this thesis. In addition, we present the comprehensive evaluation of the Feudal Stealing algorithm and the granularity-driven task selection policies using the simulations of a large class of regular and irregular parallel applications on a wide range of computing environments. We show how the Feudal Stealing algorithm and the granularity-driven task selection policies bring significant improvements in speedups of irregular applications, compared to the state-of-the-art work-stealing algorithms. Furthermore, we also present the implementation of the task selection policies in the Grid-GUM runtime system [AZ06] for Glasgow Parallel Haskell (GpH) [THLPJ98], in addition to the implementation in SCALES, and we also present the evaluation of this implementation on a large set of synthetic applications.

Automatic analysis of visual data is a key objective of computer vision research; and performing visual recognition of objects from images is one of the most important steps towards understanding and gaining insights into the visual data. Most existing approaches in the literature for the visual recognition are based on a supervised learning paradigm. Unfortunately, they require a large amount of labelled training data which severely limits their scalability. On the other hand, recognition is instantaneous and effortless for humans. They can recognise a new object without seeing any visual samples by just knowing the description of it, leveraging similarities between the description of the new object and previously learned concepts. Motivated by humans recognition ability, this thesis proposes novel approaches to tackle cross-class transfer learning (crossclass recognition) problem whose goal is to learn a model from seen classes (those with labelled training samples) that can generalise to unseen classes (those with labelled testing samples) without any training data i.e., seen and unseen classes are disjoint. Specifically, the thesis studies and develops new methods for addressing three variants of the cross-class transfer learning: Chapter 3 The first variant is transductive cross-class transfer learning, meaning labelled training set and unlabelled test set are available for model learning. Considering training set as the source domain and test set as the target domain, a typical cross-class transfer learning assumes that the source and target domains share a common semantic space, where visual feature vector extracted from an image can be embedded using an embedding function. Existing approaches learn this function from the source domain and apply it without adaptation to the target one. They are therefore prone to the domain shift problem i.e., the embedding function is only concerned with predicting the training seen class semantic representation in the learning stage during learning, when applied to the test data it may underperform. In this thesis, a novel cross-class transfer learning (CCTL) method is proposed based on unsupervised domain adaptation. Specifically, a novel regularised dictionary learning framework is formulated by which the target class labels are used to regularise the learned target domain embeddings thus effectively overcoming the projection domain shift problem. Chapter 4 The second variant is inductive cross-class transfer learning, that is, only training set is assumed to be available during model learning, resulting in a harder challenge compared to the previous one. Nevertheless, this setting reflects a real-world setting in which test data is available after the model learning. The main problem remains the same as the previous variant, that is, the domain shift problem occurs when the model learned only from the training set is applied to the test set without adaptation. In this thesis, a semantic autoencoder (SAE) is proposed building on an encoder-decoder paradigm. Specifically, first a semantic space is defined so that knowledge transfer is possible from the seen classes to the unseen classes. Then, an encoder aims to embed/project a visual feature vector into the semantic space. However, the decoder exerts a generative task, that is, the projection must be able to reconstruct the original visual features. The generative task forces the encoder to preserve richer information, thus the learned encoder from seen classes is able generalise better to the new unseen classes. Chapter 5 The third one is unsupervised cross-class transfer learning. In this variant, no supervision is available for model learning i.e., only unlabelled training data is available, leading to the hardest setting compared to the previous cases. The goal, however, is the same, learning some knowledge from the training data that can be transferred to the test data composed of completely different labels from that of training data. The thesis proposes a novel approach which requires no labelled training data yet is able to capture discriminative information. The proposed model is based on a new graph regularised dictionary learning algorithm. By introducing a l1- norm graph regularisation term, instead of the conventional squared l2-norm, the model is robust against outliers and noises typical in visual data. Importantly, the graph and representation are learned jointly, resulting in further alleviation of the effects of data outliers. As an application, person re-identification is considered for this variant in this thesis.

Thesis (Ph. D.)--University of California, Riverside, 2009. / Includes abstract. Title from first page of PDF file (viewed March 11, 2010). Available via ProQuest Digital Dissertations. Includes bibliographical references (p. 70-77). Also issued in print.

Thesis (M.S.)--Rochester Institute of Technology, 1989. / Includes bibliographical references (leaves 65-69).