ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 1 - 10 of 307
Filtering by
- All Subjects: Machine Learning
- All Subjects: philosophy
Description
Sparsity has become an important modeling tool in areas such as genetics, signal and audio processing, medical image processing, etc. Via the penalization of l-1 norm based regularization, the structured sparse learning algorithms can produce highly accurate models while imposing various predefined structures on the data, such as feature groups or graphs. In this thesis, I first propose to solve a sparse learning model with a general group structure, where the predefined groups may overlap with each other. Then, I present three real world applications which can benefit from the group structured sparse learning technique. In the first application, I study the Alzheimer's Disease diagnosis problem using multi-modality neuroimaging data. In this dataset, not every subject has all data sources available, exhibiting an unique and challenging block-wise missing pattern. In the second application, I study the automatic annotation and retrieval of fruit-fly gene expression pattern images. Combined with the spatial information, sparse learning techniques can be used to construct effective representation of the expression images. In the third application, I present a new computational approach to annotate developmental stage for Drosophila embryos in the gene expression images. In addition, it provides a stage score that enables one to more finely annotate each embryo so that they are divided into early and late periods of development within standard stage demarcations. Stage scores help us to illuminate global gene activities and changes much better, and more refined stage annotations improve our ability to better interpret results when expression pattern matches are discovered between genes.
ContributorsYuan, Lei (Author) / Ye, Jieping (Thesis advisor) / Wang, Yalin (Committee member) / Xue, Guoliang (Committee member) / Kumar, Sudhir (Committee member) / Arizona State University (Publisher)
Created2013
Description
This philosophical inquiry explores the work of philosophers Gilles Deleuze and Félix Guattari and posits applications to music education. Through the concepts of multiplicities, becoming, bodies without organs, smooth spaces, maps, and nomads, Deleuze and Guattari challenge prior and current understandings of existence. In their writings on art, education, and how might one live, they assert a world consisting of variability and motion. Drawing on Deleuze and Guattari's emphasis on time and difference, I posit the following questions: Who and when are we? Where are we? When is music? When is education? Throughout this document, their philosophical figuration of a rhizome serves as a recurring theme, highlighting the possibilities of complexity, diverse connections, and continual processes. I explore the question "When and where are we?" by combining the work of Deleuze and Guattari with that of other authors. Drawing on these ideas, I posit an ontology of humans as inseparably cognitive, embodied, emotional, social, and striving multiplicities. Investigating the question "Where are we?" using Deleuze and Guattari's writings as well as that of contemporary place philosophers and other writers reveals that humans exist at the continually changing confluence of local and global places. In order to engage with the questions "When is music?" and "When is education?" I inquire into how humans as cognitive, embodied, emotional, social, and striving multiplicities emplaced in a glocalized world experience music and education. In the final chapters, a philosophy of music education consisting of the ongoing, interconnected processes of complicating, considering, and connecting is proposed. Complicating involves continually questioning how humans' multiple inseparable qualities and places integrate during musical and educative experiences. Considering includes imagining the multiple directions in which connections might occur as well as contemplating the quality of potential connections. Connecting involves assisting students in forming variegated connections between themselves, their multiple qualities, and their glocal environments. Considering a rhizomatic philosophy of music education includes continually engaging in the integrated processes of complicating, considering, and connecting. Through such ongoing practices, music educators can promote flourishing in the lives of students and the experiences of their multiple communities.
ContributorsRicherme, Lauren Kapalka (Author) / Stauffer, Sandra (Thesis advisor) / Gould, Elizabeth (Committee member) / Schmidt, Margaret (Committee member) / Sullivan, Jill (Committee member) / Tobias, Evan (Committee member) / Arizona State University (Publisher)
Created2013
Description
This work presents two complementary studies that propose heuristic methods to capture characteristics of data using the ensemble learning method of random forest. The first study is motivated by the problem in education of determining teacher effectiveness in student achievement. Value-added models (VAMs), constructed as linear mixed models, use students’ test scores as outcome variables and teachers’ contributions as random effects to ascribe changes in student performance to the teachers who have taught them. The VAMs teacher score is the empirical best linear unbiased predictor (EBLUP). This approach is limited by the adequacy of the assumed model specification with respect to the unknown underlying model. In that regard, this study proposes alternative ways to rank teacher effects that are not dependent on a given model by introducing two variable importance measures (VIMs), the node-proportion and the covariate-proportion. These VIMs are novel because they take into account the final configuration of the terminal nodes in the constitutive trees in a random forest. In a simulation study, under a variety of conditions, true rankings of teacher effects are compared with estimated rankings obtained using three sources: the newly proposed VIMs, existing VIMs, and EBLUPs from the assumed linear model specification. The newly proposed VIMs outperform all others in various scenarios where the model was misspecified. The second study develops two novel interaction measures. These measures could be used within but are not restricted to the VAM framework. The distribution-based measure is constructed to identify interactions in a general setting where a model specification is not assumed in advance. In turn, the mean-based measure is built to estimate interactions when the model specification is assumed to be linear. Both measures are unique in their construction; they take into account not only the outcome values, but also the internal structure of the trees in a random forest. In a separate simulation study, under a variety of conditions, the proposed measures are found to identify and estimate second-order interactions.
ContributorsValdivia, Arturo (Author) / Eubank, Randall (Thesis advisor) / Young, Dennis (Committee member) / Reiser, Mark R. (Committee member) / Kao, Ming-Hung (Committee member) / Broatch, Jennifer (Committee member) / Arizona State University (Publisher)
Created2013
Description
ABSTRACT In this work, I provide two novel pieces of evidence in favor of the view that there is pragmatic encroachment on knowledge. First, I present an empirical case via the results of a series of recent experiments to show that folk-knowledge attributions may be sensitive to time constraints even when the latter are construed in a non-truth relevant manner. Along the way, I consider some comments made by Jonathan Schaffer (2006) as it pertains to interpreting time constraints-sensitivity in a manner that supports contextualism, before offering reasons to resist such a treatment. I proceed by applying interest relative invariantism to adjudicate a conflict in the epistemology of testimony namely, the positive reasons requirement a la, reductionism vs. non-reductionism. In particular, I highlight how whether an epistemic subject H needs positive non-testimonial reasons to be justified in accepting S's testimony that p, depends on what is at stake for H in believing that p and how much time H has in deliberating about p.
ContributorsShin, Joseph Ellis (Author) / Pinillos, N. Angel (Thesis advisor) / Reynolds, Steven L (Committee member) / White, Michael J. (Committee member) / Arizona State University (Publisher)
Created2013
Description
Emergentism offers a promising compromise in the philosophy of mind between Cartesian substance dualism and reductivistic physicalism. The ontological emergentist holds that conscious mental phenomena supervene on physical phenomena, but that they have a nature over and above the physical. However, emergentist views have been subjected to a variety of powerful objections: they are alleged to be self-contradictory, incompatible with mental causation, justified by unreliable intuitions, and in conflict with our contemporary scientific understanding of the world. I defend the emergentist position against these objections. I clarify the concepts of supervenience and of ontological novelty in a way that ensures the emergentist position is coherent, while remaining distinct from physicalism and traditional dualism. Making note of the equivocal way in which the concept of sufficiency is used in Jaegwon Kim's arguments against emergent mental causation, I argue that downward causation does not entail widespread overdetermination. I argue that considerations of ideal a priori deducibility from some physical base, or "Cosmic Hermeneutics", will not themselves provide answers to where the cuts in the structure of nature lie. Instead, I propose reconsidering the question of Cosmic Hermeneutics in terms of which cognitive resources would be required for the ideal reasoner to perform the deduction. Lastly, I respond to the objection that emergence in the philosophy of mind is in conflict with our contemporary scientific understanding of the world. I suggest that a kind of weak ontological emergence is a viable form of explanation in many fields, and discuss current applications of emergence in biology, sociology, and the study of complex systems.
ContributorsWatson, Jeffrey (Author) / Kobes, Bernard W (Thesis advisor) / Pinillos, Nestor (Committee member) / Horgan, Terence (Committee member) / Reynolds, Steven (Committee member) / Arizona State University (Publisher)
Created2013
Description
This thesis explores the conceptual span and plausibility of emergence and its applicability to the problem of mental causation. The early parts of the project explicate a distinction between weak and strong emergence as described by Jaegwon Kim. They also consider Kim's objections regarding the conceptual incoherence of strong emergence and the otiose nature of weak emergence. The paper then explores Mark Bedau's in-between conception of emergence and ultimately finds that middle conception to be both coherent and useful. With these three emergence distinctions in hand, the thesis goes on to explore Evan Thompson's recent work - Mind in Life (2010). In that work, Thompson advances a strong emergence approach to mind, whereby he concludes the incipient stages of cognition are found at the most basic levels of life, namely - biologic cells. Along the way, Thompson embraces holism and a nonfundamental
onhierarchical physics in order to counter Jaegwon Kim's objections to the notion of downward causation needed for strong emergence. The thesis presents arguments against Thompson's holism and nonfundamental physics, while supporting his assertion regarding the incipient stages of cognition. It then combines an important distinction between mental causation and the experience of mental causation with Thompson's notion of incipient cognition to arrive at a dual realms approach to understanding mental causation.
onhierarchical physics in order to counter Jaegwon Kim's objections to the notion of downward causation needed for strong emergence. The thesis presents arguments against Thompson's holism and nonfundamental physics, while supporting his assertion regarding the incipient stages of cognition. It then combines an important distinction between mental causation and the experience of mental causation with Thompson's notion of incipient cognition to arrive at a dual realms approach to understanding mental causation.
ContributorsFournier, Thomas (Author) / Kobes, Bernard W (Thesis advisor) / Reynolds, Steven L (Committee member) / Armendt, Brad (Committee member) / Arizona State University (Publisher)
Created2013
Description
Saying, "if Mary had watered Sam's plant, it wouldn't have died," is an ordinary way to identify Mary not watering Sam's plant as the cause of its death. But there are problems with this statement. If we identify Mary's omitted action as the cause, we seemingly admit an inordinate number of omissions as causes. For any counterfactual statement containing the omitted action is true (e.g. if Hillary Clinton had watered Sam's plant, it wouldn't have died). The statement, moreover, is mysterious because it is not clear why one protasis is more salient than any alternatives such as "if Sam hadn't gone to Bismarck." In the burgeoning field of experimental metaphysics, some theorists have tried to account for these intuitions about omissive causes. By synthesizing this data and providing a few experiments, I will suggest that judgments - and maybe metaphysics - about omissive causes necessarily have a normative feature. This understanding of omissive causes may be able to adequately resolve the problems above.
ContributorsHenne, Paul (Author) / Kobes, Bernard W (Thesis advisor) / Pinillos, Nestor A (Thesis advisor) / Reynolds, Steven (Committee member) / Arizona State University (Publisher)
Created2013
Description
With the number of internationally-run clinical drug trials increasing, the double standards between those in developed nations and those in developing nations are being scrutinized under the ethical microscope. Many argue that several pharmaceutical companies and researchers are exploiting developing nation participants. Two issues of concern are the use of a placebo control when an effective alternative treatment exists and the lack of drug availability to the country that hosted the clinical trial should the experimental drug prove effective. Though intuitively this seems like an instance of exploitation, philosophically, exploitation theories cannot adequately account for the wrongdoing in these cases. My project has two parts. First, after explaining why the theories of Alan Wertheimer, John Lawrence Hill, and Ruth Sample fail to explain the exploitation in clinical drug research, I provide an alternative account of exploitation that can explain why the double standard in clinical research is harmful. Rather than craft a single theory encompassing all instances of exploitation, I offer an account of a type, or subset, of exploitation that I refer to as comparative exploitation. The double standards in clinical research fall under the category of comparative exploitation. Furthermore, while many critics maintain that cases of comparative exploitation, including clinical research, are mutually beneficial, they are actually harmful to its victims. I explain the harm of comparative exploitation using Ben Bradley's counterfactual account of harm and Larry May's theory of sharing responsibility. The second part of my project focuses on the "standard of care" argument, which most defenders use to justify the double standard in clinical research. I elaborate on Ruth Macklin's position that advocates of the "standard of care" position make three faulty assumptions: placebo-controlled trials are the gold standard, the only relevant question responsive to the host country's health needs is "Is the experimental product being studied better than the 'nothing' now available to the population?", and the only way of obtaining affordable products is to test cheap alternatives to replace the expensive ones. In the end, I advocate moving towards a universalizing of standards in order to avoid exploitation.
ContributorsFundora, Danielle (Author) / McGregor, Joan (Thesis advisor) / Brake, Elizabeth (Committee member) / Portmore, Douglas (Committee member) / Arizona State University (Publisher)
Created2013
Description
The present essay addresses the epistemic difficulties involved in achieving consensus with respect to the Hayek-Keynes debate. In particular, it is argued that the debate cannot be settled on the basis of the observable evidence; or, more precisely, that the empirical implications of the theories of Hayek and Keynes are such that, regardless of what is observed, both of the theories can be interpreted as true, or at least, not falsified. Regardless of the evidence, both Hayek and Keynes can be interpreted as right. The underdetermination of theories by evidence is an old and ubiquitous problem in science. The present essay makes explicit the respects in which the empirical evidence underdetermines the choice between the theories of Hayek and Keynes. In particular, it is argued both that there are convenient responses one can offer that protect each theory from what appears to be threatening evidence (i.e., that the choice between the two theories is underdetermined in the holist sense) and that, for particular kinds of evidence, the two theories are empirically equivalent (i.e., with respect to certain kinds of evidence, the choice between the two theories is underdetermined in the contrastive sense).
ContributorsScheall, Scott (Author) / Creath, Richard (Thesis advisor) / Armendt, Brad (Committee member) / French, Peter (Committee member) / Arizona State University (Publisher)
Created2012
Description
Image understanding has been playing an increasingly crucial role in vision applications. Sparse models form an important component in image understanding, since the statistics of natural images reveal the presence of sparse structure. Sparse methods lead to parsimonious models, in addition to being efficient for large scale learning. In sparse modeling, data is represented as a sparse linear combination of atoms from a "dictionary" matrix. This dissertation focuses on understanding different aspects of sparse learning, thereby enhancing the use of sparse methods by incorporating tools from machine learning. With the growing need to adapt models for large scale data, it is important to design dictionaries that can model the entire data space and not just the samples considered. By exploiting the relation of dictionary learning to 1-D subspace clustering, a multilevel dictionary learning algorithm is developed, and it is shown to outperform conventional sparse models in compressed recovery, and image denoising. Theoretical aspects of learning such as algorithmic stability and generalization are considered, and ensemble learning is incorporated for effective large scale learning. In addition to building strategies for efficiently implementing 1-D subspace clustering, a discriminative clustering approach is designed to estimate the unknown mixing process in blind source separation. By exploiting the non-linear relation between the image descriptors, and allowing the use of multiple features, sparse methods can be made more effective in recognition problems. The idea of multiple kernel sparse representations is developed, and algorithms for learning dictionaries in the feature space are presented. Using object recognition experiments on standard datasets it is shown that the proposed approaches outperform other sparse coding-based recognition frameworks. Furthermore, a segmentation technique based on multiple kernel sparse representations is developed, and successfully applied for automated brain tumor identification. Using sparse codes to define the relation between data samples can lead to a more robust graph embedding for unsupervised clustering. By performing discriminative embedding using sparse coding-based graphs, an algorithm for measuring the glomerular number in kidney MRI images is developed. Finally, approaches to build dictionaries for local sparse coding of image descriptors are presented, and applied to object recognition and image retrieval.
ContributorsJayaraman Thiagarajan, Jayaraman (Author) / Spanias, Andreas (Thesis advisor) / Frakes, David (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013