Dissertation (PhD)--University of Arizona, Tucson, Arizona, 2006.

No description available.

Thesis (PhD) - Swinburne University of Technology, Faculty of Engineering and Industrial Sciences, Centre for Advanced Internet Architectures, 2009. / A thesis submitted for the degree of Doctor of Philosophy, Centre for Advanced Internet Architectures, Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, 2009. Typescript. Bibliography: p. 218-240.

Early time series classification is the task of predicting the class label of a time series before it is observed in its entirety. In time-sensitive domains where information is collected over time it is worth sacrificing some classification accuracy in favor of earlier predictions, ideally early enough for actions to be taken. However, since accuracy and earliness are contradictory objectives, a solution to this problem must find a task-dependent trade-off. There are two common state-of-the-art methods. The first involves an analyst selecting a timestep at which all predictions must be made. This does not capture earliness on a case-by-case basis, so if the selecting timestep is too early, all later signals are missed, and if a signal happens early, the classifier still waits to generate a prediction. The second method is the exhaustive search for signals, which encodes no timing information and is not scalable to high dimensions or long time series. We design the first early classification model called EARLIEST to tackle this multi-objective optimization problem, jointly learning (1) to decide at which time step to halt and generate predictions and (2) how to classify the time series. Each of these is learned based on the task and data features. We achieve an analyst-controlled balance between the goals of earliness and accuracy by pairing a recurrent neural network that learns to classify time series as a supervised learning task with a stochastic controller network that learns a halting-policy as a reinforcement learning task. The halting-policy dictates sequential decisions, one per timestep, of whether or not to halt the recurrent neural network and classify the time series early. This pairing of networks optimizes a global objective function that incorporates both earliness and accuracy. We validate our method via critical clinical prediction tasks in the MIMIC III database from the Beth Israel Deaconess Medical Center along with another publicly available time series classification dataset. We show that EARLIEST out-performs two state-of-the-art LSTM-based early classification methods. Additionally, we dig deeper into our model's performance using a synthetic dataset which shows that EARLIEST learns to halt when it observes signals without having explicit access to signal locations. The contributions of this work are three-fold. First, our method is the first neural network-based solution to early classification of time series, bringing the recent successes of deep learning to this problem. Second, we present the first reinforcement-learning based solution to the unsupervised nature of early classification, learning the underlying distributions of signals without access to this information through trial and error. Third, we propose the first joint-optimization of earliness and accuracy, allowing learning of complex relationships between these contradictory goals.

Thesis (M.S.)--Rochester Institute of Technology, 2008. / Typescript. Includes bibliographical references (leaves 65-68).

This dissertation presents an historical analysis of teachers’ participation in policy making with specific reference to the South African Schools’ Act (SASA) of 1996. The central aim of the study was to explore the opportunities, extent and outcomes of teachers’ participation in the development of SASA and the various factors that attest to its complexity. Main argument and claims While acknowledging the broader political, ideological and economic context of teacherstate relations in policy making, this study contends that macro-forces in themselves are insufficient in explaining the dynamics of policy making and teachers’ role in it. Teachers’ participation in policy making is shaped, as powerfully, by factors such as partisan alliances and policy capacity, and by specific school contexts. Fundamental to this argument is the importance attached to the notion of ‘historical specificity’, which provides the overall thread that binds the diverse forces and factors that shaped the nature of teachers’ participation in policy making. In making the above argument, this thesis posits the following main claims: • Teachers’ participation in the development of SASA was historically-determined and shaped by the ambiguous and political nature of teacher-state relations, underpinned by ideological allegiance and flexibility. Key factors that shaped this relationship were government and teacher unions’ harnessing of the ideologies of unionism and professionalism, the ability of teacher unions’ to resist state cooptation and teacher unions’ agency in the cultivation of policy networks, especially partisan and non-partisan alliances; • Teachers’ participation was influenced by the specificity of South Africa’s transition to democracy, particularly the developmental tendency of the postapartheid education state and the politics of compromise that underpinned the Teachers’ participation in policy making: The case of the South African Schools Act vi political transition. Thus, in spite of ‘global’ forces, ‘local’ dynamics were ultimately more instrumental in determining the nature and impact of teachers’ participation in the policy making process; • The ‘stakeholder’ or ‘representative’ form of participation which characterized SASA’s development has underlined the limits of participation founded on a western, liberal model of democracy and stressed the value of direct (participatory) and deliberative models of democracy. Teachers as individuals, therefore, experience ‘dual marginalization’ in the policy arena, firstly, because state policy makers do not consult or engage them, and secondly because teacher unions themselves are often unable to adequately involve grassroots’ members in policy formulation activities within their organisations; • Teachers’ participation in the development of SASA has been dominated by the adoption of a rational and expert-driven model of policy making, wherein the views and contributions of experts are more highly valued than those of ordinary citizens, including teachers. At the same time, the study underlines the importance of a strong organisational basis for teachers’ participation in policy making, particularly the need for well-functioning organizational structures and policy expertise within the ranks of teacher unions themselves; and • Teachers’ participation in policy making is not confined to hopes of influencing policy outcomes. It is about social and policy learning and its implications for teachers’ daily practice and for the organizational development of teacher unions. Main theoretical and methodological contributions The study offers an eclectic conceptual framework for research into teachers’ participation in policy making, drawing on the disciplines of history, political science and education policy, which can be considered by researchers undertaking similar studies especially in transitional contexts. In so doing, the study makes the following contributions: Teachers’ participation in policy making: The case of the South African Schools Act vii It presents teacher unions and policy makers with a more comprehensive perspective to consider when formulating policy; It contributes a novel perspective for examining the relationship between education, civil society and the state in South Africa and countries undergoing transition worldwide; and It provides substance for comparative discussions on teachers’ participation in policy formulation globally. Finally, the study reclaims history as a method of social enquiry in policy analysis and in contrast to existing studies with its largely a-historical policy implementation bias, refocuses the empirical analysis on the policy development process and dynamics.

One of the hardest challenges in building a realistic Bayesian network (BN) model is to construct the node probability tables (NPTs). Even with a fixed predefined model structure and very large amounts of relevant data, machine learning methods do not consistently achieve great accuracy compared to the ground truth when learning the NPT entries (parameters). Hence, it is widely believed that incorporating expert judgment or related domain knowledge can improve the parameter learning accuracy. This is especially true in the sparse data situation. Expert judgments come in many forms. In this thesis we focus on expert judgment that specifies inequality or equality relationships among variables. Related domain knowledge is data that comes from a different but related problem. By exploiting expert judgment and related knowledge, this thesis makes novel contributions to improve the BN parameter learning performance, including: • The multinomial parameter learning model with interior constraints (MPL-C) and exterior constraints (MPL-EC). This model itself is an auxiliary BN, which encodes the multinomial parameter learning process and constraints elicited from the expert judgments. • The BN parameter transfer learning (BNPTL) algorithm. Given some potentially related (source) BNs, this algorithm automatically explores the most relevant source BN and BN fragments, and fuses the selected source and target parameters in a robust way. • A generic BN parameter learning framework. This framework uses both expert judgments and transferred knowledge to improve the learning accuracy. This framework transfers the mined data statistics from the source network as the parameter priors of the target network. Experiments based on the BNs from a well-known repository as well as two realworld case studies using different data sample sizes demonstrate that the proposed new approaches can achieve much greater learning accuracy compared to other state-of-theart methods with relatively sparse data.

An increasing number of models have been proposed to explain the link structure observed in complex networks. The central problem addressed in this thesis is: how do we select the best model? The model-selection method we implement is based on supervised learning. We train a classifier on six complex network models incorporating various link attachment mechanisms, including preferential attachment, copying and spatial. For the classification we represent graphs as feature vectors, integrating common complex network statistics with raw counts of small connected subgraphs commonly referred to as graphlets. The outcome of each experiment strongly indicates that models which incorporate the preferential attachment mechanism fit the network structure of Facebook the best. The experiments also suggest that graphlet structure is better at distinguishing different network models than more traditional complex network statistics. To further the understanding of our experimental results, we compute the expected number of triangles, 3-paths and 4-cycles which appear in our selected models. This analysis shows that the spatial preferential attachment model generates 3-paths, triangles and 4-cycles in abundance, giving a closer match to the observed network structure of the Facebook networks used in our model selection experiment. The other models generate some of these subgraphs in abundance but not all three at once. In general, we show that our selected models generate vastly different amounts of triangles, 3-paths and 4-cycles, verifying our experimental conclusion that graphlets are distinguishing features of these complex network models.

Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2007. / Includes bibliographical references (leaves 80-88). Also available in electronic version.

The aim of this doctoral thesis is to present a body of work aimed at reducing the time spent by animators manually constructing keyframed animation. To this end we present a number of state of the art machine learning techniques applied to the domain of character animation. Data-driven tools for the synthesis and production of character animation have a good track record of success. In particular, they have been adopted thoroughly in the games industry as they allow designers as well as animators to simply specify the high-level descriptions of the animations to be created, and the rest is produced automatically. Even so, these techniques have not been thoroughly adopted in the film industry in the production of keyframe based animation [Planet, 2012]. Due to this, the cost of producing high quality keyframed animation remains very high, and the time of professional animators is increasingly precious. We present our work in four main chapters. We first tackle the key problem in the adoption of data-driven tools for key framed animation - a problem called the inversion of the rig function. Secondly, we show the construction of a new tool for data-driven character animation called the motion manifold - a representation of motion constructed using deep learning that has a number of properties useful for animation research. Thirdly, we show how the motion manifold can be extended as a general tool for performing data-driven animation synthesis and editing. Finally, we show how these techniques developed for keyframed animation can also be adapted to advance the state of the art in the games industry.