Theses and Dissertations
This collection includes both ASU Theses and Dissertations, submitted by graduate students, and the Barrett, Honors College theses submitted by undergraduate students.
Displaying 1 - 10 of 46
Filtering by
- Genre: Doctoral Dissertation
- Creators: Berisha, Visar
Description
Intuitive decision making refers to decision making based on situational pattern recognition, which happens without deliberation. It is a fast and effortless process that occurs without complete awareness. Moreover, it is believed that implicit learning is one means by which a foundation for intuitive decision making is developed. Accordingly, the present study investigated several factors that affect implicit learning and the development of intuitive decision making in a simulated real-world environment: (1) simple versus complex situational patterns; (2) the diversity of the patterns to which an individual is exposed; (3) the underlying mechanisms. The results showed that simple patterns led to higher levels of implicit learning and intuitive decision-making accuracy than complex patterns; increased diversity enhanced implicit learning and intuitive decision-making accuracy; and an embodied mechanism, labeling, contributes to the development of intuitive decision making in a simulated real-world environment. The results suggest that simulated real-world environments can provide the basis for training intuitive decision making, that diversity is influential in the process of training intuitive decision making, and that labeling contributes to the development of intuitive decision making. These results are interpreted in the context of applied situations such as military applications involving remotely piloted aircraft.
ContributorsCovas-Smith, Christine Marie (Author) / Cooke, Nancy J. (Thesis advisor) / Patterson, Robert (Committee member) / Glenberg, Arthur (Committee member) / Homa, Donald (Committee member) / Arizona State University (Publisher)
Created2011
Description
Most people are experts in some area of information; however, they may not be knowledgeable about other closely related areas. How knowledge is generalized to hierarchically related categories was explored. Past work has found little to no generalization to categories closely related to learned categories. These results do not fit well with other work focusing on attention during and after category learning. The current work attempted to merge these two areas of by creating a category structure with the best chance to detect generalization. Participants learned order level bird categories and family level wading bird categories. Then participants completed multiple measures to test generalization to old wading bird categories, new wading bird categories, owl and raptor categories, and lizard categories. As expected, the generalization measures converged on a single overall pattern of generalization. No generalization was found, except for already learned categories. This pattern fits well with past work on generalization within a hierarchy, but do not fit well with theories of dimensional attention. Reasons why these findings do not match are discussed, as well as directions for future research.
ContributorsLancaster, Matthew E (Author) / Homa, Donald (Thesis advisor) / Glenberg, Arthur (Committee member) / Chi, Michelene (Committee member) / Brewer, Gene (Committee member) / Arizona State University (Publisher)
Created2013
Description
Recent findings in human interactions with complex objects, objects with unpredictable interaction dynamics, revealed predictability as an important factor when determining effective control strategies. The current study extended these findings by examining the role of predictability in the selection of control strategies in two scenarios: during initial interactions with a novel, complex object, and when intentional constraints are imposed. In Experiment 1, methods with which people can identify and improve their control strategy during initial interactions with a complex object were examined. Participants actively restricted their movements at first to simplify the object’s complex behavior, then gradually adjusted movements to improve the system’s predictability. In Experiment 2, predictability of participants’ control strategies was monitored when the intention to act was changed to prioritize speed over stability. Even when incentivized to seek alternative strategies, people still prioritized predictability, and would compensate for the loss of predictability. These experiments furthered understanding of the motor control processes as a whole and may reveal important implications when generalized to other domains that also interact with complex systems.
ContributorsNguyen, Tri Duc (Author) / Amazeen, Eric (Thesis advisor) / Glenberg, Arthur (Committee member) / Amazeen, Polemnia G (Committee member) / Brewer, Gene (Committee member) / Arizona State University (Publisher)
Created2022
Description
The purpose of the Preschool Intervention for Embodied Storytelling (PIES) study was to evaluate the efficacy of a drama-based story time intervention on at-risk preschool students’ emotion knowledge, story retell and story comprehension skills. Six classrooms with 44 students were randomly assigned into drama-based intervention and dialogic reading control groups. After four weeks of intervention sessions twice per week, students’ emotion knowledge and story retell skills were assessed with distal measures. During the program, students’ comprehension of the stories was evaluated weekly. Participants did not show significant main effects on any measures, however investigation of simple effects revealed differences in gains over time for intervention students in their story retell skills. Despite lack of significance, effect sizes for story retell were promising. Mean differences in story comprehension skills were consistently in favor of the intervention group for the duration of the program. Teacher participants showed an increase in their positive perceptions of drama-based instruction, but their own use of these strategies at story time was variable before and after observing the PIES program. Drama based instruction through PIES may be a favorable intervention strategy for preschool students as they develop narrative skills that are a prerequisite for future reading comprehension success.
ContributorsPierce, Melissa (Author) / Restrepo, Maria Adelaida (Thesis advisor) / Glenberg, Arthur (Committee member) / Marley, Scott (Committee member) / Arizona State University (Publisher)
Created2022
Description
Generative models are deep neural network-based models trained to learn the underlying distribution of a dataset. Once trained, these models can be used to sample novel data points from this distribution. Their impressive capabilities have been manifested in various generative tasks, encompassing areas like image-to-image translation, style transfer, image editing, and more. One notable application of generative models is data augmentation, aimed at expanding and diversifying the training dataset to augment the performance of deep learning models for a downstream task. Generative models can be used to create new samples similar to the original data but with different variations and properties that are difficult to capture with traditional data augmentation techniques. However, the quality, diversity, and controllability of the shape and structure of the generated samples from these models are often directly proportional to the size and diversity of the training dataset. A more extensive and diverse training dataset allows the generative model to capture overall structures present in the data and generate more diverse and realistic-looking samples.
In this dissertation, I present innovative methods designed to enhance the robustness and controllability of generative models, drawing upon physics-based, probabilistic, and geometric techniques. These methods help improve the generalization and controllability of the generative model without necessarily relying on large training datasets. I enhance the robustness of generative models by integrating classical geometric moments for shape awareness and minimizing trainable parameters. Additionally, I employ non-parametric priors for the generative model's latent space through basic probability and optimization methods to improve the fidelity of interpolated images. I adopt a hybrid approach to address domain-specific challenges with limited data and controllability, combining physics-based rendering with generative models for more realistic results.
These approaches are particularly relevant in industrial settings, where the training datasets are small and class imbalance is common. Through extensive experiments on various datasets, I demonstrate the effectiveness of the proposed methods over conventional approaches.
ContributorsSingh, Rajhans (Author) / Turaga, Pavan (Thesis advisor) / Jayasuriya, Suren (Committee member) / Berisha, Visar (Committee member) / Fazli, Pooyan (Committee member) / Arizona State University (Publisher)
Created2023
Description
This dissertation centers on the development of Bayesian methods for learning differ- ent types of variation in switching nonlinear gene regulatory networks (GRNs). A new nonlinear and dynamic multivariate GRN model is introduced to account for different sources of variability in GRNs. The new model is aimed at more precisely capturing the complexity of GRN interactions through the introduction of time-varying kinetic order parameters, while allowing for variability in multiple model parameters. This model is used as the drift function in the development of several stochastic GRN mod- els based on Langevin dynamics. Six models are introduced which capture intrinsic and extrinsic noise in GRNs, thereby providing a full characterization of a stochastic regulatory system. A Bayesian hierarchical approach is developed for learning the Langevin model which best describes the noise dynamics at each time step. The trajectory of the state, which are the gene expression values, as well as the indicator corresponding to the correct noise model are estimated via sequential Monte Carlo (SMC) with a high degree of accuracy. To address the problem of time-varying regulatory interactions, a Bayesian hierarchical model is introduced for learning variation in switching GRN architectures with unknown measurement noise covariance. The trajectory of the state and the indicator corresponding to the network configuration at each time point are estimated using SMC. This work is extended to a fully Bayesian hierarchical model to account for uncertainty in the process noise covariance associated with each network architecture. An SMC algorithm with local Gibbs sampling is developed to estimate the trajectory of the state and the indicator correspond- ing to the network configuration at each time point with a high degree of accuracy. The results demonstrate the efficacy of Bayesian methods for learning information in switching nonlinear GRNs.
ContributorsVélez-Cruz, Nayely (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Moraffah, Bahman (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2023
Description
In the standard pipeline for machine learning model development, several design decisions are made largely based on trial and error. Take the classification problem as an example. The starting point for classifier design is a dataset with samples from the classes of interest. From this, the algorithm developer must decide which features to extract, which hypothesis class to condition on, which hyperparameters to select, and how to train the model. The design process is iterative with the developer trying different classifiers, feature sets, and hyper-parameters and using cross-validation to pick the model with the lowest error. As there are no guidelines for when to stop searching, developers can continue "optimizing" the model to the point where they begin to "fit to the dataset". These problems are amplified in the active learning setting, where the initial dataset may be unlabeled and label acquisition is costly. The aim in this dissertation is to develop algorithms that provide ML developers with additional information about the complexity of the underlying problem to guide downstream model development. I introduce the concept of "meta-features" - features extracted from a dataset that characterize the complexity of the underlying data generating process. In the context of classification, the complexity of the problem can be characterized by understanding two complementary meta-features: (a) the amount of overlap between classes, and (b) the geometry/topology of the decision boundary. Across three complementary works, I present a series of estimators for the meta-features that characterize overlap and geometry/topology of the decision boundary, and demonstrate how they can be used in algorithm development.
ContributorsLi, Weizhi (Author) / Berisha, Visar (Thesis advisor) / Dasarathy, Gautam (Thesis advisor) / Natesan Ramamurthy, Karthikeyan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2022
Description
Severe forms of mental illness, such as schizophrenia and bipolar disorder, are debilitating conditions that negatively impact an individual's quality of life. Additionally, they are often difficult and expensive to diagnose and manage, placing a large burden on society. Mental illness is typically diagnosed by the use of clinical interviews and a set of neuropsychiatric batteries; a key component of nearly all of these evaluations is some spoken language task. Clinicians have long used speech and language production as a proxy for neurological health, but most of these assessments are subjective in nature. Meanwhile, technological advancements in speech and natural language processing have grown exponentially over the past decade, increasing the capacity of computer models to assess particular aspects of speech and language. For this reason, many have seen an opportunity to leverage signal processing and machine learning applications to objectively assess clinical speech samples in order to automatically compute objective measures of neurological health. This document summarizes several contributions to expand upon this body of research. Mainly, there is still a large gap between the theoretical power of computational language models and their actual use in clinical applications. One of the largest concerns is the limited and inconsistent reliability of speech and language features used in models for assessing specific aspects of mental health; numerous methods may exist to measure the same or similar constructs and lead researchers to different conclusions in different studies. To address this, a novel measurement model based on a theoretical framework of speech production is used to motivate feature selection, while also performing a smoothing operation on features across several domains of interest. Then, these composite features are used to perform a much wider range of analyses than is typical of previous studies, looking at everything from diagnosis to functional competency assessments. Lastly, potential improvements to address practical implementation challenges associated with the use of speech and language technology in a real-world environment are investigated. The goal of this work is to demonstrate the ability of speech and language technology to aid clinical practitioners toward improvements in quality of life outcomes for their patients.
ContributorsVoleti, Rohit Nihar Uttam (Author) / Berisha, Visar (Thesis advisor) / Liss, Julie M (Thesis advisor) / Turaga, Pavan (Committee member) / Spanias, Andreas (Committee member) / Arizona State University (Publisher)
Created2022
Description
In the era of big data, more and more decisions and recommendations are being made by machine learning (ML) systems and algorithms. Despite their many successes, there have been notable deficiencies in the robustness, rigor, and reliability of these ML systems, which have had detrimental societal impacts. In the next generation of ML, these significant challenges must be addressed through careful algorithmic design, and it is crucial that practitioners and meta-algorithms have the necessary tools to construct ML models that align with human values and interests. In an effort to help address these problems, this dissertation studies a tunable loss function called α-loss for the ML setting of classification. The alpha-loss is a hyperparameterized loss function originating from information theory that continuously interpolates between the exponential (alpha = 1/2), log (alpha = 1), and 0-1 (alpha = infinity) losses, hence providing a holistic perspective of several classical loss functions in ML. Furthermore, the alpha-loss exhibits unique operating characteristics depending on the value (and different regimes) of alpha; notably, for alpha > 1, alpha-loss robustly trains models when noisy training data is present. Thus, the alpha-loss can provide robustness to ML systems for classification tasks, and this has bearing in many applications, e.g., social media, finance, academia, and medicine; indeed, results are presented where alpha-loss produces more robust logistic regression models for COVID-19 survey data with gains over state of the art algorithmic approaches.
ContributorsSypherd, Tyler (Author) / Sankar, Lalitha (Thesis advisor) / Berisha, Visar (Committee member) / Dasarathy, Gautam (Committee member) / Kosut, Oliver (Committee member) / Arizona State University (Publisher)
Created2022
Description
Dealing with relational data structures is central to a wide-range of applications including social networks, epidemic modeling, molecular chemistry, medicine, energy distribution, and transportation. Machine learning models that can exploit the inherent structural/relational bias in the graph structured data have gained prominence in recent times. A recurring idea that appears in all approaches is to encode the nodes in the graph (or the entire graph) as low-dimensional vectors also known as embeddings, prior to carrying out downstream task-specific learning. It is crucial to eliminate hand-crafted features and instead directly incorporate the structural inductive bias into the deep learning architectures.
In this dissertation, deep learning models that directly operate on graph structured data are proposed for effective representation learning. A literature review on existing graph representation learning is provided in the beginning of the dissertation. The primary focus of dissertation is on building novel graph neural network architectures that are robust against adversarial attacks. The proposed graph neural network models are extended to multiplex graphs (heterogeneous graphs). Finally, a relational neural network model is proposed to operate on a human structural connectome. For every research contribution of this dissertation, several empirical studies are conducted on benchmark datasets. The proposed graph neural network models, approaches, and architectures demonstrate significant performance improvements in comparison to the existing state-of-the-art graph embedding strategies.
ContributorsShanthamallu, Uday Shankar (Author) / Spanias, Andreas (Thesis advisor) / Thiagarajan, Jayaraman J (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2021