Artificial Intelligence and Robotics Commons^™

Deployment-Aware Deep Learning For Computer Vision: Efficient Architectures From 3d Segmentation To Mixed Reality, Bahar Uddin Mahmud

Dissertations

Deep learning has become the dominant approach for solving vision-centric problems; however, its successful deployment in real-world applications remains limited by high computational cost, data dependency, and insufficient integration with practical and human-centered environments. While state-of-the art deep learning models often achieve impressive performance in controlled settings, they frequently fail to generalize or operate efficiently under deployment constraints such as limited resources, complex data modalities, and real-time interaction requirements. These limitations motivate the need for a deployment-oriented deep learning framework that balances accuracy, efficiency, and practical usability.

This dissertation investigates the design and deployment of efficient deep learning architectures for …

Quantum And Conventional Informatics Studies Of Synthesis Energetics And Defect Formation In Nitride Crystal Epitaxy, Andrew Steven Messecar

Dissertations

Machine learning is a valuable approach for the processing and analysis of complex information. By estimating relationships from recorded data, machine learning methodologies can be effective strategies for pattern recognition, enabling investigations and technological applications based thereon. The potential for improved understanding of high-dimensional data has drawn interest towards machine learning from across the sciences, including the research and development of new and improved material systems. In the context of experimental materials research, much of the reported efforts to incorporate machine learning into conventional practice have been primarily focused on either the enhanced analysis of characterization experiment data or the …

Principles Of Privacy And Security In Artificial Intelligence And Applications, Khang Tran

Dissertations

Modern artificial intelligence (AI) systems have transformed critical domains such as healthcare, software engineering, finance, and the legal system. Despite their broad impact, concerns about trustworthiness, especially regarding privacy and security, remain major obstacles to wider adoption. Addressing these concerns requires both a systematic understanding of the privacy and security risks inherent in AI systems and the development of principled foundations for trustworthy AI that safeguard client privacy and security. This goal is particularly challenging because of the complexity of modern large-scale AI systems, the trade-offs between privacy and model utility, and the need to simultaneously ensure other important properties …

Holistic Dram Enhancements: From Intrinsic In-Memory Operations To Robust Security Mechanisms, Ranyang Zhou

Dissertations

Dynamic Random-Access Memory (DRAM) is both the performance bottleneck and a critical security boundary of modern computing systems. Its physical properties make it an attractive substrate for near-data computation—yet those same properties expose it to disturbance-based hardware attacks. This dissertation argues that these two dimensions are not independent: the architectural choices that make DRAM efficient also reshape its threat landscape. Addressing both requires a unified approach to memory architecture and security co-design.

The first part of this dissertation attacks the memory wall through four processing-in-DRAM (PIM) frameworks. ReD-LUT and LT-PIM unify lookup-table arithmetic with charge-sharing logic, achieving up to 37.8x …

A Generative Ai-Driven Computational Framework For Industry-Scale Discovery Of Novel Battery Materials, Joy Datta

Dissertations

The growing demand for sustainable, high-energy-density electrochemical storage has motivated the exploration of multivalent-ion batteries based on earth-abundant elements such as aluminum, calcium, magnesium, and zinc. While multivalent charge carriers offer higher theoretical energy density than lithium, their practical deployment is hindered by sluggish ion transport, strong ion-host interactions, and structural degradation of electrode materials. Identifying host materials that can reversibly accommodate multivalent ions while maintaining structural integrity remains a fundamental challenge. The dissertation develops a scalable, end-to-end computational framework that integrates density functional theory (DFT), machine learning (ML), and generative artificial intelligence (GenAI) to accelerate the discovery of next-generation …

Toward Learning-Based Reconstruction And Part Decomposition Of Man-Made 3d Geometry: Neural Implicit Representations And Scalable Supervision, Shen Fan

Dissertations

Digital three-dimensional (3D) models are central to engineering design, analysis, and manufacturing, but learning pipelines for man-made geometry often operate on sampled carriers that do not preserve all of the structure present in exact CAD representations. This dissertation studies learning-based reconstruction and part decomposition for structured man-made 3D geometry, from general object benchmarks to CAD-derived datasets, with a focus on neural implicit representations trained from signed-distance samples, point clouds, and tessellated meshes. The goal is to make these models more accurate, more part-aware, and more consistently supervised.

First, signed distance function (SDF) reconstruction with implicit neural representations is improved through …

Federated Neuromorphic Intelligence: Advancing Robustness, Efficiency, And Continual Adaptation In Edge Environments, Manh V. Nguyen

Dissertations

This dissertation investigates how spiking neural networks (SNNs) can improve federated edge intelligence by advancing three interconnected goals: communication efficiency, adversarial robustness, and continual adaptation. As edge computing deployments expand across Internet of Things (IoT), sensing, and privacy-sensitive applications, conventional federated learning approaches built around artificial neural networks (ANNs) face growing limitations in power consumption, bandwidth demand, and resilience to real-world uncertainty. SNNs offer an alternative computational paradigm based on event-driven, sparse, and temporally structured processing that is naturally suited to constrained edge environments. However, their behavior in practical federated settings remains insufficiently understood.

To address this gap, this dissertation …

How Principals Who Use Artificial Intelligence For Innovation Create Cognitive Equity While Principals Who Use Ai For Efficiency Create Cognitive Debt, Jethro Jones

Dissertations

This dissertation in practice examined whether a targeted professional learning   intervention could shift school leaders’ use of generative artificial intelligence (AI) from efficiency-oriented tasks toward innovation-oriented strategic problem solving. AI is typically adopted to accelerate existing routines, which can deepen “cognitive debt” by reinforcing ineffective practices rather than improving systems. This study advanced a “cognitive equity” frame, positioning AI as a tool that can expand principals’ cognitive capacity to address complex problems and lead adaptive change. Using a quasi-experimental, single-group design, the study evaluated a free, full-day AI for Innovation workshop, which emphasized foundational understanding of how AI tools work …

Privacy Preserving-Based Artificial Intelligence For Precision Agriculture, Partha P. Sengupta

Dissertations

The research work finds a solution to precision agriculture of cotton cultivation using artificial intelligence (AI) models. Two sets of model performance based on the application are selected namely a low resource and a high resource setting. This is because using drone surveys to capture images identifying the classes of stressed and unstressed cotton plantation requires limited model architecture and CPU based computation. Thus, traditional AI models were selected for low resource settings. Again, for high computation intensive models like transfer learning-convolution neural network (CNN) based architectures were grouped into high resource settings. There was another issue of class imbalance …

Robust Ai Solutions For Financial Markets Through Generative Modeling, Dynamic Graph Learning, And Reinforcement-Based Portfolio Optimization, Jingyi Gu

Dissertations

Financial markets are inherently uncertain and dynamic, driven by complex factors such as macroeconomic signals, investor sentiment, and evolving inter-asset relationships. While machine learning has advanced financial modeling, existing approaches often fall short in addressing the real-world intricacies of finance. This dissertation confronts two critical challenges, human-driven stochasticity and risk-intensive decision-making under real-world trading constraints, while seizing a pivotal opportunity, the structural dynamics of evolving financial systems. These elements are foundational to advancing robust and practical financial intelligence.

To this end, this dissertation develops a unified framework for robust financial modeling and decision-making. The framework is architected as a progressive, …

Optimizing Hip And Knee Assistance For Walking And Sit-To-Stand Transitions: An Intrinsic Muscle Mechanics Based Predictive Approach, Neethan Ratnakumar

Dissertations

As the global population ages, the demand for wearable assistive technologies continues to rise, driven by their potential to enhance mobility and independence in older adults. Effectively designed controllers for lower-limb exoskeletons to assist sit-to-stand (STS) and walking are crucial for delivering efficient, safe, and comfortable assistance during daily activities. Traditionally, controller optimization involves biomechanical modeling and user-specific customization. Musculoskeletal simulations play a central role in this process by providing insights into human-exoskeleton interaction dynamics, thereby informing and refining control strategies.

This work presents a simulation-driven approach for developing exoskeleton controllers for walking and STS using two distinct methods: optimal …

Machine Learning And Optimization For Intelligent Decision-Making, Elson Cibaku

Dissertations

This dissertation presents a series of innovative machine learning and optimization model designs that address complex operational challenges across logistics and power systems. By integrating advanced neural architectures with robust optimization techniques, the work delivers scalable solutions designed to improve efficiency, reliability, and decision-making in dynamic and real-world environments. The first study introduces a two-stage approach to effective vaccine distribution. This framework tackles the capacitated vehicle routing problem by combining adaptive clustering techniques with reinforcement learning and a simulated annealing pickup policy. Through extensive computational experiments, the approach demonstrates substantial improvements in routing efficiency, reducing both computational time and logistical …

Model-Based Reinforcement Learning And Deep Learning For Power Converter Circuit Design Automation, Shaoze Fan

Dissertations

This dissertation presents a comprehensive automated framework for power converter design, leveraging reinforcement learning (RL) and graph-transformer networks (GTN) to address critical inefficiencies in traditional manual topology optimization. Motivated by the combinatorial increase of circuit design spaces and the computational cost of iterative simulations, this work develops a robust framework for generating energy-efficient topologies requiring rapid and reliable circuit design.

The framework integrates three key components: (1) an upper-confidence-bound-tree-based (UCT-based) RL model for circuit topology space exploration, (2) parallelized UCT algorithms to accelerate exploration processes, (3) a Graph-Transformer-based Network enabling fast circuit performance evaluation. Experimental validation demonstrates the whole framework …

Adversarial Robustness In Advanced Machine Learning Models Integrating Graph Neural Networks And Large Language Models, Mahmoud Nazzal

Dissertations

Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle these structures; Graph Neural Networks (GNNs) for relational mining and Large Language Models (LLMs) for sequential understanding. Despite their success, these models face challenges in security, robustness, and interpretability. GNNs excel in relational reasoning but are vulnerable to adversarial manipulation and lack interpretability, while LLMs are strong in linguistic reasoning and generalization yet struggle with relational data and …

Enriching Vision Representation By Deep Neural Networks And Self-Supervised Learning, Yucong Shen

Dissertations

Nowadays, more and more interesting computer vision tasks are tackled by deep learning approaches. However, the increasing model complexity imposes significant computational and storage costs. To address this challenge, this dissertation explores efficient deep learning techniques, proposing morphological layer, an efficient feature extraction layer. It achieves competitive image classification accuracy with significantly decreased model parameters. Another attempt at efficient deep learning is a proposed channel pruning approach that compresses deep neural networks by identifying and removing redundant channels using optimal transport theory. This approach achieves significant reductions in model size and computational cost while maintaining or even improving performance across …

From Neural Networks To Large Language Models: Innovations In Financial Ai, Mathematical Reasoning, And Structured Data Representation, Junyi Ye

Dissertations

This dissertation explores the evolution and application of artificial intelligence techniques across three critical domains: financial modeling, mathematical reasoning, and structured data analysis. The dissertation presents seven research projects that chart a progression from specialized neural architectures to sophisticated large language models (LLMs), contributing novel methodologies and frameworks at each stage.

In the financial domain, the research first introduces TS-Mixer, a MLP-based architecture for time-series forecasting that captures both feature relationships and temporal dependencies through a simple yet effective design, outperforming more complex models in S&P500 index prediction. The dissertation then presents DySTAGE, a dynamic graph representation learning framework that …

Pushing The Boundaries Of Large Language Models: Innovations And Limitations In Nlp, Finance, And Mathematics, A M Muntasir Rahman

Dissertations

Large Language Models (LLMs) have emerged as transformative tools across a spectrum of domains, yet their practical deployment reveals a blend of remarkable potential and notable limitations. This research explores innovative methodologies to extend the capabilities of LLMs while addressing critical challenges in their evaluation and application. By leveraging rule-based approaches, the in-context learning capabilities of LLMs, and human-in-the-loop validation across three focused studies, this research introduces robust strategies for dataset synthesis, model enhancement, and model assessment in three distinct domains: natural language processing, financial sentiment analysis, and mathematical reasoning

The first study proposes an efficient data augmentation framework, EASE, …

Federated Learning Systems For Mobile Sensing Data, Xiaopeng Jiang

Dissertations

Federated Learning (FL) has emerged as a new distributed Deep Learning (DL) paradigm that enables privacy-aware training and inference on mobile devices with help from the cloud. This dissertation presents a comprehensive exploration of FL with mobile sensing data, covering systems, applications, and optimizations.

First, a mobile-cloud FL system, FLSys, is designed to balance model performance with resource consumption, tolerate communication failures, and achieve scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. In addition, FLSys provides advanced privacy-preserving mechanisms and a common API for third-party app developers to …

An Experimental Study Of Supervised Machine Learning Techniques For Minor Class Prediction Utilizing Kernel Density Estimation: Factors Impacting Model Performance, Abdullah Mana Alfarwan

Dissertations

This dissertation examined classification outcome differences among four popular individual supervised machine learning (ISML) models (logistic regression, decision tree, support vector machine, and multilayer perceptron) when predicting minor class membership within imbalanced datasets. The study context and the theoretical population sampled focus on one aspect of the larger problem of student retention and dropout prediction in higher education (HE): identification.

This study differs from current literature by implementing an experimental design approach with simulated student data that closely mirrors HE situational and student data. Specifically, this study tested the predictive ability of the four ISML classification models (CLS) under experimentally …

Sensing With Integrity: Responsible Sensor Systems In An Era Of Ai, David Eisenberg

Dissertations

Deep and machine learning now offer immense benefits for consumer choice, decision-making, medicine, mental health and education, smart cities, and intelligent transportation and driver safety. However, as communication and Internet technology further advances, these benefits have the potential to be outweighed by compromises to privacy, personal freedom, consumer trust, and discrimination. While ethical consequences for personal freedom and equity rise from these technological advances, the issue may not be the technology itself but a lack of regulation and policy that allow abuses to occur. A first study examines how emerging sensor-based technologies, limited to only accelerometer and gyroscope data from …

Enhancing Rotating Machinery Fault Diagnosis: A Dual-Head Attention Mechanism In Deep Learning Neural Networks, Qing Snyder

Dissertations

Rotating machinery is crucial to production efficiency and safety in manufacturing industries for an extended time. Ensuring machinery reliability necessitates effective diagnostic systems, particularly for rotating bearings, the key components of such equipment. Fault diagnosis in rotating machinery is essential to prevent failures and minimize downtime, thereby playing an important role in industrial operations. The application of advanced neural network techniques in industry has risen recently. Among these, attention-based neural networks, especially the Transformer models, are originally noteworthy for their sequential data handling capability. This research delves into attention-based algorithms for rotating machinery fault diagnosis, signifying a substantial advancement in …

Multi-Modality Transformer For E-Commerce: Inferring User Purchase Intention To Bridge The Query-Product Gap, Srivatsa Mallapragada

Dissertations

The rapid growth of e-commerce has necessitated the development of sophisticated product retrieval systems that can effectively match user queries with relevant products. However, the semantic gap between queries and products remains a significant challenge, as traditional retrieval methods often fail to capture the nuances of user purchase intentions. E-commerce click-stream data and product catalogs offer critical user behavior insights and product knowledge that are untapped in the current product search algorithms. This dissertation presents learning strategies that leverage the query-product transaction logs to enrich the pipeline of our proposed multi-modal transformer model, which transforms initial user queries into pseudo …

Unraveling Biases And Customer Heterogeneity In E-Commerce Recommendation Systems, Sachin Sharma

Dissertations

This research explores the biases present in AI algorithms within e-commerce recommendation systems, focusing on how these biases prioritize popular, sponsored, and private-label products over actual customer preferences. We extend the responsible AI discourse by critically examining these biases and their implications for fairness in e-commerce. To strengthen the current understanding of AI fairness in the fields of information systems and computer science, we aim to challenge the assumption that AI fairness is objective and the same for everyone. We examine how individual differences, such as equity sensitivity and exchange ideology, contribute to users' varied perceptions of AI fairness. Through …

Quantifying Balance: Computational And Learning Frameworks For The Characterization Of Balance In Bipedal Systems, Kubra Akbas

Dissertations

In clinical practice and general healthcare settings, the lack of reliable and objective balance and stability assessment metrics hinders the tracking of patient performance progression during rehabilitation; the assessment of bipedal balance plays a crucial role in understanding stability and falls in humans and other bipeds, while providing clinicians important information regarding rehabilitation outcomes. Bipedal balance has often been examined through kinematic or kinetic quantities, such as the Zero Moment Point and Center of Pressure; however, analyzing balance specifically through the body's Center of Mass (COM) state offers a holistic and easily comprehensible view of balance and stability.

Building upon …

Learning Representations For Effective And Explainable Software Bug Detection And Fixing, Yi Li

Dissertations

Software has an integral role in modern life; hence software bugs, which undermine software quality and reliability, have substantial societal and economic implications. The advent of machine learning and deep learning in software engineering has led to major advances in bug detection and fixing approaches, yet they fall short of desired precision and recall. This shortfall arises from the absence of a 'bridge,' known as learning code representations, that can transform information from source code into a suitable representation for effective processing via machine and deep learning.

This dissertation builds such a bridge. Specifically, it presents solutions for effectively learning …

Fortifying Robustness: Unveiling The Intricacies Of Training And Inference Vulnerabilities In Centralized And Federated Neural Networks, Guanxiong Liu

Dissertations

Neural network (NN) classifiers have gained significant traction in diverse domains such as natural language processing, computer vision, and cybersecurity, owing to their remarkable ability to approximate complex latent distributions from data. Nevertheless, the conventional assumption of an attack-free operating environment has been challenged by the emergence of adversarial examples. These perturbed samples, which are typically imperceptible to human observers, can lead to misclassifications by the NN classifiers. Moreover, recent studies have uncovered the ability of poisoned training data to generate Trojan backdoored classifiers that exhibit misclassification behavior triggered by predefined patterns.

In recent years, significant research efforts have been …

On Explainability Of Neural Networks, Cem Benar

Dissertations

It is widely reported that deep neural networks outperform most competitors for a range of applications. The state-of-the-art neural networks have built-in inductive bias of architectural choices, regularizations, optimizer types, and initialization methods. Using inductive bias is intuitive to enhance the model approximation. Deep neural networks are mostly dense and heavily overparameterized. They tend to be biased towards low-rank solutions to reduce complexity and improve generalization performance, known as implicit regularization. The implicit regularization as observed in specific architectures and various real-world data sets suggests to overparameterize neural networks judiciously and learn compressed representations (lower rank approximation) with improved performance. …

Machine Learning And Network Embedding Methods For Gene Co-Expression Networks, Niloofar Aghaieabiane

Dissertations

High-throughput technologies such as DNA microarrays and RNA-seq are used to measure the expression levels of large numbers of genes simultaneously. To support the extraction of biological knowledge, individual gene expression levels are transformed into Gene Co-expression Networks (GCNs). GCNs are analyzed to discover gene modules. GCN construction and analysis is a well-studied topic, for nearly two decades. While new types of sequencing and the corresponding data are now available, the software package WGCNA and its most recent variants are still widely used, contributing to biological discovery.

The discovery of biologically significant modules of genes from raw expression data is …

Deep Hybrid Modeling Of Neuronal Dynamics Using Generative Adversarial Networks, Soheil Saghafi

Dissertations

Mechanistic modeling and machine learning methods are powerful techniques for approximating biological systems and making accurate predictions from data. However, when used in isolation these approaches suffer from distinct shortcomings: model and parameter uncertainty limit mechanistic modeling, whereas machine learning methods disregard the underlying biophysical mechanisms. This dissertation constructs Deep Hybrid Models that address these shortcomings by combining deep learning with mechanistic modeling. In particular, this dissertation uses Generative Adversarial Networks (GANs) to provide an inverse mapping of data to mechanistic models and identifies the distributions of mechanistic model parameters coherent to the data.

Chapter 1 provides background information on …

Loss Scaling And Step Size In Deep Learning Optimizatio, Nora Alosily

Dissertations

Deep learning training consumes ever-increasing time and resources, and that is
due to the complexity of the model, the number of updates taken to reach good
results, and both the amount and dimensionality of the data. In this dissertation,
we will focus on making the process of training more efficient by focusing on the
step size to reduce the number of computations for parameters in each update.
We achieved our objective in two new ways: we use loss scaling as a proxy for
the learning rate, and we use learnable layer-wise optimizers. Although our work
is perhaps not the first …