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 201 - 210 of 212
Filtering by
- Creators: Simonson, Mark
- Creators: Turaga, Pavan
Description
This thesis presents robust and novel solutions using knowledge distillation with geometric approaches and multimodal data that can address the current challenges in deep learning, providing a comprehensive understanding of the learning process involved in knowledge distillation. Deep learning has attained significant success in various applications, such as health and wellness promotion, smart homes, and intelligent surveillance. In general, stacking more layers or increasing the number of trainable parameters causes deep networks to exhibit improved performance. However, this causes the model to become large, resulting in an additional need for computing and power resources for training, storage, and deployment. These are the core challenges in incorporating such models into small devices with limited power and computational resources. In this thesis, robust solutions aimed at addressing the aforementioned challenges are presented. These proposed methodologies and algorithmic contributions enhance the performance and efficiency of deep learning models. The thesis encompasses a comprehensive exploration of knowledge distillation, an approach that holds promise for creating compact models from high-capacity ones, while preserving their performance. This exploration covers diverse datasets, including both time series and image data, shedding light on the pivotal role of augmentation methods in knowledge distillation. The effects of these methods are rigorously examined through empirical experiments. Furthermore, the study within this thesis delves into the efficient utilization of features derived from two different teacher models, each trained on dissimilar data representations, including time-series and image data. Through these investigations, I present novel approaches to knowledge distillation, leveraging geometric techniques for the analysis of multimodal data. These solutions not only address real-world challenges but also offer valuable insights and recommendations for modeling in new applications.
ContributorsJeon, Eunsom (Author) / Turaga, Pavan (Thesis advisor) / Li, Baoxin (Committee member) / Lee, Hyunglae (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2023
ContributorsTong, Ethan (Author) / Simonson, Mark (Thesis director) / Kelly, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2023-12
ContributorsTong, Ethan (Author) / Simonson, Mark (Thesis director) / Kelly, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2023-12
ContributorsTong, Ethan (Author) / Simonson, Mark (Thesis director) / Kelly, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2023-12
ContributorsTong, Ethan (Author) / Simonson, Mark (Thesis director) / Kelly, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2023-12
DescriptionInvestment thesis and recommendation of Outbrain (NYSE: OB), a leading AdTech Company
ContributorsTong, Ethan (Author) / Simonson, Mark (Thesis director) / Kelly, Robert (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2023-12
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
The rapid expansion of artificial intelligence has propelled significant growth in the GPU market. In the evolving data center landscape, Company X faces challenges due to its lag in entering the GPU market, which jeopardizes its competitive advantage against industry players like Nvidia and AMD. To address these issues, our thesis aims to analyze market dynamics between CPUs and GPUs-whether they present distinct markets or compete against each other. We seek to guide Company X in maximizing profitability and sustaining its pivotal role in the semiconductor industry amidst the AI revolution. Specifically, we discuss optimizing their GPU offering, Falcon Shores, towards specific markets and doubling down on the production of CPUs.
ContributorsMostaghimi, Dunya (Author) / Kujawa, Brennan (Co-author) / Ulreich-Power, Cameron (Co-author) / Livesay, Thomas (Co-author) / Simonson, Mark (Thesis director) / Hertzel, Mike (Committee member) / Barrett, The Honors College (Contributor) / Department of Economics (Contributor)
Created2024-05
Description
This project examines entry-level processors for Company X. Analyzing their current position and creating recommendations for their future positioning in regard to entry-level processors. Utilizing financial models, our group worked to determine the most effective way to optimize NPV and gross margin for this segment. With extensive step models and sensitivity analysis, we analyzed potential paths that Company X could take. Continuing to be mindful of the limitations that certain projected paths would entail. Through our analysis, we were able to form a comprehensive suggestion that had a positive 8-year NPV and an improved gross margin percentage.
ContributorsJones, Ciara (Author) / Kuo, Ian (Co-author) / Mathias, Chase (Co-author) / Huseinovic, Ayla (Co-author) / Simonson, Mark (Thesis director) / Hertzel, Michael (Committee member) / Barrett, The Honors College (Contributor) / Department of Finance (Contributor)
Created2024-05
Description
In the rapidly evolving field of computer vision, propelled by advancements in deeplearning, the integration of hardware-software co-design has become crucial to overcome
the limitations of traditional imaging systems. This dissertation explores the integration
of hardware-software co-design in computational imaging, particularly in light transport
acquisition and Non-Line-of-Sight (NLOS) imaging. By leveraging projector-camera
systems and computational techniques, this thesis address critical challenges in imaging
complex environments, such as adverse weather conditions, low-light scenarios, and the
imaging of reflective or transparent objects.
The first contribution in this thesis is the theory, design, and implementation of a slope
disparity gating system, which is a vertically aligned configuration of a synchronized
raster scanning projector and rolling-shutter camera, facilitating selective imaging through
disparity-based triangulation. This system introduces a novel, hardware-oriented approach
to selective imaging, circumventing the limitations of post-capture processing.
The second contribution of this thesis is the realization of two innovative approaches
for spotlight optimization to improve localization and tracking for NLOS imaging. The
first approach utilizes radiosity-based optimization to improve 3D localization and object
identification for small-scale laboratory settings. The second approach introduces a learningbased
illumination network along with a differentiable renderer and NLOS estimation
network to optimize human 2D localization and activity recognition. This approach is
validated on a large, room-scale scene with complex line-of-sight geometries and occluders.
The third contribution of this thesis is an attention-based neural network for passive
NLOS settings where there is no controllable illumination. The thesis demonstrates realtime,
dynamic NLOS human tracking where the camera is moving on a mobile robotic platform. In addition, this thesis contains an appendix featuring temporally consistent
relighting for portrait videos with applications in computer graphics and vision.
ContributorsChandran, Sreenithy (Author) / Jayasuriya, Suren (Thesis advisor) / Turaga, Pavan (Committee member) / Dasarathy, Gautam (Committee member) / Kubo, Hiroyuki (Committee member) / Arizona State University (Publisher)
Created2024