Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

2025

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 1711 - 1740 of 3497

Full-Text Articles in Computer Sciences

Bridging Cattle Farming And Technology: The Development Of Moomanager, Matthew Hayes May 2025

Bridging Cattle Farming And Technology: The Development Of Moomanager, Matthew Hayes

Honors College Theses

Small-scale cattle producers face persistent challenges in adopting digital tools for herd management, often due to barriers such as limited digital literacy, software complexity, and poor alignment with practical workflows. Existing literature highlights the potential benefits of mobile applications in agricultural contexts, yet adoption rates remain low among smaller operations. This thesis investigates how a streamlined, mobile-first application can address these adoption barriers while supporting essential farm management tasks. The study details the design and development of MooManager, a mobile application built with React Native and Supabase and structured around core features such as cattle tracking, beef sales logging, and …

Go to article

Optimized Student Grouping For Enhanced Classroom Performance, Kathryn E. Reardon May 2025

Optimized Student Grouping For Enhanced Classroom Performance, Kathryn E. Reardon

Honors Theses

Effective grouping methods enhance classroom collaboration and allow for a student-centered teaching approach; however, traditional grouping methods are time-consuming, subjective, and can create inconsistent group dynamics. This project addresses these challenges by employing a data-driven approach to optimize student groups based on academic performance, behavior, attendance, language barriers, and teacher preferences. The minimum viable product is a web application with an algorithm-driven system to group students and a database storage for group results. During the initiation phase, a problem was defined with a proposed solution. During the planning phase, potential design choices and grouping methods were researched and assessed. During …

Go to article

Effective And Efficient Graph Foundation Model, Lecheng Kong May 2025

Effective And Efficient Graph Foundation Model, Lecheng Kong

McKelvey School of Engineering Graduate Student Theses & Dissertations

Graph data has emerged as a central component in numerous real-world applications, spanning recommender systems, drug discovery, social networking, and traffic forecasting. While traditional and modern graph learning techniques—ranging from graph kernels to Graph Neural Networks (GNNs) and graph transformers—have achieved significant success, their task-specific nature and reliance on supervised learning limit their adaptability to new, unseen tasks. This rigidity becomes especially problematic in dynamic environments where retraining for every new task is costly and often infeasible. Inspired by the transformative impact of foundation models in natural language processing, this thesis explores the feasibility of developing a graph foundation model—a …

Go to article

Scaling Quantum Systems: Quantum Networks, Distributed Quantum Computing, And Security, Zebo Yang May 2025

Scaling Quantum Systems: Quantum Networks, Distributed Quantum Computing, And Security, Zebo Yang

McKelvey School of Engineering Graduate Student Theses & Dissertations

Recent advancements in quantum computing have opened up new possibilities across various fields, offering significant potential to enhance computation, communication, cryptography, and applications in areas like sensing, medicine, and chemistry. However, the capabilities of individual quantum devices are still limited, and scaling quantum hardware monolithically presents substantial challenges. Interconnecting quantum systems offers a promising alternative by aggregating capabilities across a network, thereby enabling quantum advantages for larger and more practical problems. This interconnection is achieved through quantum networking, which links external quantum systems, and Distributed Quantum Computing (DQC), which connects quantum processors within a system, such as in quantum data …

Go to article

System Security Foundations For Ai-Enabled Systems, Yuhao Wu May 2025

System Security Foundations For Ai-Enabled Systems, Yuhao Wu

McKelvey School of Engineering Graduate Student Theses & Dissertations

AI is being deployed broadly, from conventional computing systems like IoT systems to more advanced agentic systems. It is shifting from being a specialized component responsible for specific functions to becoming the core of agentic systems, where it drives autonomous decision-making and task execution. These AI-enabled systems bring tremendous benefits. For example, large language models can interpret user intent, select appropriate tools, and access data to complete tasks with minimal human guidance. However, they also introduce new security, privacy, and safety risks. These risks arise not only from the models themselves but also from the broader system design and integration. …

Go to article

Towards Secure And Privacy-Preserving Machine Learning Systems, Han Liu May 2025

Towards Secure And Privacy-Preserving Machine Learning Systems, Han Liu

McKelvey School of Engineering Graduate Student Theses & Dissertations

In recent years, machine learning (ML) has advanced at an unprecedented pace, driving the widespread adoption of increasingly sophisticated models across a broad range of real-world applications, including healthcare, finance, autonomous systems, and critical infrastructure. While these models have delivered remarkable benefits and transformed numerous industries, they remain inherently vulnerable to a variety of security and privacy threats. Given their growing role in safety-critical domains, ensuring their security and privacy has become imperative. Systematically addressing these vulnerabilities requires comprehensive adversarial analyses to uncover weaknesses and inform the design of robust defenses. This dissertation systematically investigates ML vulnerabilities in adversarial settings …

Go to article

Trustworthy Autonomy Through Robust Control And Alignment, Junlin Wu May 2025

Trustworthy Autonomy Through Robust Control And Alignment, Junlin Wu

McKelvey School of Engineering Graduate Student Theses & Dissertations

As artificial intelligence systems are increasingly applied in safety critical domains such as robotics, autonomous driving, and decision making under uncertainty, ensuring their trustworthiness has become a central challenge. This dissertation addresses two major facets of trustworthy AI: reliable control through formal guarantees and alignment against adversarial manipulation. The first part of the dissertation focuses on provably stable, robust, and safe control for nonlinear systems using learning based methods. We introduce the first general framework for synthesizing neural Lyapunov controllers in discrete time systems. This method combines a sound verifier based on mixed integer linear programming with gradient based counterexample …

Go to article

Understanding And Mitigating Timing Issues In Autonomous Systems, Ao Li May 2025

Understanding And Mitigating Timing Issues In Autonomous Systems, Ao Li

McKelvey School of Engineering Graduate Student Theses & Dissertations

Autonomous systems, such as self-driving cars and drones, have become a part of our daily lives. Since these systems operate in and interact with the physical world, their correctness depends on both functional and temporal aspects. However, the increasing complexity of modern computing hardware and software often leads to unpredictable timing behavior in these systems, making temporal properties particularly challenging to ensure. This dissertation proposes novel approaches to specify and enforce temporal properties based on a comprehensive empirical study of real-world issues. The first half of this dissertation presents an empirical study that dissects the timing issues. The dissection begins …

Go to article

Identification Of Subtypes Of Post-Stroke And Neurotypical Gait Behaviors Using Neural Network Analysis Of Gait Cycle Kinematics, Andrian Kuch, Nicolas Schweighofer, James M. Finley, Alison Mckenzie, Yuxin Wen, Natalia Sánchez May 2025

Identification Of Subtypes Of Post-Stroke And Neurotypical Gait Behaviors Using Neural Network Analysis Of Gait Cycle Kinematics, Andrian Kuch, Nicolas Schweighofer, James M. Finley, Alison Mckenzie, Yuxin Wen, Natalia Sánchez

Physical Therapy Faculty Articles and Research

Gait impairment post-stroke is highly heterogeneous. Prior studies classified heterogeneous gait patterns into subgroups using peak kinematics, kinetics, or spatiotemporal variables. A limitation of this approach is the need to select discrete features in the gait cycle. Using continuous gait cycle data, we accounted for differences in magnitude and timing of kinematics. Here, we propose a machine-learning pipeline combining supervised and unsupervised learning. We first trained a Convolutional Neural Network and a Temporal Convolutional Network to extract features that distinguish impaired from neurotypical gait. Then, we used unsupervised time-series k-means and Gaussian Mixture Models to identify gait clusters. We tested …

Go to article

Magic: The Gathering Deck Testing And Optimization, Ian B. Watson May 2025

Magic: The Gathering Deck Testing And Optimization, Ian B. Watson

Honors Theses

The goal of this project is to provide a tool for players of the trading card game Magic: the Gathering to determine whether or not a given deck is optimally built by outputting relevant information regarding its optimality. This is done through a simulator that plays a one-sided game, recording what cards are played, what turn they are played, and how much mana is left over at the end of every turn. The simulator was tested with both optimized and unoptimized decks to show how it can be used to diagnose both.

Go to article

Automation Of Javanese Shadow Puppets Using Machine Control, Kristian Rice, Yinson Tso, Mukhammadali Yuldoshev May 2025

Automation Of Javanese Shadow Puppets Using Machine Control, Kristian Rice, Yinson Tso, Mukhammadali Yuldoshev

Publications and Research

The virtualization of Javanese shadow puppetry (Wayang Kulit) offers a unique opportunity to preserve and revitalize traditional performance art through immersive digital platforms. This project explores the development of a virtual Wayang Kulit experience using real-time 3D engines like Unity/Unreal Engine while focusing on simulating the mechanics and aesthetics of shadow puppet performance. The puppets are designed using detailed 2D planes and rigged with skeletal systems to reflect the stylized motion of traditional puppetry. An aspect of this project is integrating an AI-driven control system that autonomously animates the puppets, learning from recorded puppeteer performances to replicate gesture, rhythm, and …

Go to article

Reverse Engineering Of Binary Programs Using Graph Attention Networks, Sai Nikhila Kanigiri May 2025

Reverse Engineering Of Binary Programs Using Graph Attention Networks, Sai Nikhila Kanigiri

Master's Theses

Understanding the functionality and behavior of binary code is essential for many software engineering tasks, including malware analysis, vulnerability detection, and program optimization. However, automating this process is challenging due to the complexity of machine code and the significant manual effort required from experienced software engineers. In this paper, we present BinGAT (Reverse Engineering of Binary Programs using Graph Attention Networks), a method for classifying binary programs into algorithmic categories using Graph Attention Neural Networks (GNNs) based on their Control-Flow Graphs (CFGs). Given a binary program, BinGAT extracts its CFG through static analysis and transforms the assembly instructions within each …

Go to article

Computational Design Of Potent Sirna For Braf Oncogene Silencing For Enhancing Cancer Therapy, Muhammad Hermawan Widyananda, Ricadonna Raissa May 2025

Computational Design Of Potent Sirna For Braf Oncogene Silencing For Enhancing Cancer Therapy, Muhammad Hermawan Widyananda, Ricadonna Raissa

Karbala International Journal of Modern Science

The discovery of oncogenic BRAF mutations has prompted the development of inhibitors, yet resistance remains widespread. A more effective strategy involves targeting BRAF mRNA with siRNA to overcome resistance to BRAF inhibitors. This study aims to design potent siRNA for BRAF oncogene silencing using a computational approach. The full coding sequence of BRAF was retrieved from the NCBI database and potential siRNAs were predicted using the Ui-Tei, Reynolds, and Amarzguioui rules. Identified siRNAs were further analyzed using various prediction systems and parameters, including their interaction with the hAgo2 protein. The results identified that seven siRNAs (siRNA 23, siRNA 24, siRNA …

Go to article

Algorithmically Optimal Outer Measures, J. H. Lutz, Neil Lutz May 2025

Algorithmically Optimal Outer Measures, J. H. Lutz, Neil Lutz

Computer Science Faculty Works

We investigate the relationship between algorithmic fractal dimensions and the classical local fractal dimensions of outer measures in Euclidean spaces. We introduce global and local optimality conditions for lower semicomputable outer measures. We prove that globally optimal outer measures exist. Our main theorem states that the classical local fractal dimensions of any locally optimal outer measure coincide exactly with the algorithmic fractal dimensions. Our proof uses an especially convenient locally optimal outer measure κ defined in terms of Kolmogorov complexity. We discuss implications for point-to-set principles.

Go to article

Development Of Interactive Games On An Affordable Braille Display, Daniel Tsivkovski, Dylan Ravel, Maryam Etezad May 2025

Development Of Interactive Games On An Affordable Braille Display, Daniel Tsivkovski, Dylan Ravel, Maryam Etezad

Student Scholar Symposium Abstracts and Posters

Developing an affordable and STEM learning-focused Braille display addresses a significant disparity in the market for Braille displays, where most fail to provide a cost-effective, accessible, and education-oriented solution. This research aims to bridge this gap through innovative hardware and software development, offering a comprehensive learning experience to elementary school children (K-6) who are blind/visually impaired. The hardware features a piezo-electric tactile display that displays up to six Braille characters at once or a shape in an 8x8 pin array configuration. The educational software includes a user-friendly website packed with engaging STEM activities specifically designed for blind/visually impaired children. The …

Go to article

Exploring Human-Centered Principles To Improve Lecture Slides, Joshua Harlev, Louanne Boyd May 2025

Exploring Human-Centered Principles To Improve Lecture Slides, Joshua Harlev, Louanne Boyd

Student Scholar Symposium Abstracts and Posters

As a university emphasizing student participation and attention, lectures are central to the educational experience at Chapman. However, slide-based lectures can widely vary in quality and approach. Considering various debunkings of learning styles over the years, it seems more difficult than ever to understand how to most effectively teach students. Effective use of computerized tools has thus become increasingly important as the pace of change continues to increase. Yet, research is available on the effectiveness of teaching methods that can provide guidelines for instructors. With increasingly connected and capable devices at our fingertips, it is imperative to both use the …

Go to article

Praxly: An Online Ide For The Praxis Cs Test Pseudocode, Benjamin Saupp May 2025

Praxly: An Online Ide For The Praxis Cs Test Pseudocode, Benjamin Saupp

James Madison Undergraduate Research Journal (JMURJ)

No abstract provided.

Go to article

Optimizing Information Security In Cloud Environments: A Risk Management Approach And Guide For Enterprise Cloud Security, Joshua Olusegun Oyeniyi, Oluwashina Akinloye Oyeniran May 2025

Optimizing Information Security In Cloud Environments: A Risk Management Approach And Guide For Enterprise Cloud Security, Joshua Olusegun Oyeniyi, Oluwashina Akinloye Oyeniran

Journal of Cybersecurity Education, Research and Practice

In recent years, cloud computing has become increasingly integral to organizational operations due to its scalability, accessibility and cost effectiveness in managing data and resources. However, the rise in security threats and attacks on cloud environments necessitates having robust measures in place to protect data confidentiality, integrity and availability. This paper presents an optimized approach to cloud information security management by reviewing the current threat landscape, evaluating key risk management frameworks, and provided practical solutions for enhancing enterprise cloud security. The study examined three leading cloud security frameworks: the Cloud Controls Matrix (CCM) known for its cloud-specific controls, the NIST …

Go to article

Satellite Reorientation Using Reinforcement Learning Under Unknown Attitude Failure, Matthew Willoughby May 2025

Satellite Reorientation Using Reinforcement Learning Under Unknown Attitude Failure, Matthew Willoughby

Doctoral Dissertations and Master's Theses

This study presents a reinforcement learning (RL) approach for reestablishing communication with deep-space satellites under unknown attitude determination and control system (ADCS) failures. When traditional fault-tolerant control methods cannot restore signal, the proposed RL controller acts as a last-resort measure by autonomously reorienting the satellite’s antenna toward Earth while charging the battery via solar panels. A generic reward function, designed for the RL-based method, enables the controller to adapt to diverse failure scenarios, including severe actuator noise, misalignment, and complete actuator failure. Simulations are conducted in the Basilisk environment and trained with the tonic framework and demonstrate ranging capabilities of …

Go to article

Mapping The Key Players In Kawasaki Disease; Role Of Inflammatory Genes And Protein-Protein Interactions, Wael Hafez, Feras Al-Obeidat, Asrar Rashid, Afsheen Raza, Nouran Hamza, Nesma Ahmed, Marwa M. Abdeljawad, Raziya Kadwa, Abdelhameed Elmesery, Muneir Gador, Dina Khair, Gihan Zina, Fatema Abdulaal, Mina Wassef Girgiss, Maha Abdelhadi, Ahmed Abdelrahman, Mahmad Anwar Ibrahim, Mohamed El Sherbiny May 2025

Mapping The Key Players In Kawasaki Disease; Role Of Inflammatory Genes And Protein-Protein Interactions, Wael Hafez, Feras Al-Obeidat, Asrar Rashid, Afsheen Raza, Nouran Hamza, Nesma Ahmed, Marwa M. Abdeljawad, Raziya Kadwa, Abdelhameed Elmesery, Muneir Gador, Dina Khair, Gihan Zina, Fatema Abdulaal, Mina Wassef Girgiss, Maha Abdelhadi, Ahmed Abdelrahman, Mahmad Anwar Ibrahim, Mohamed El Sherbiny

All Works

Background: Kawasaki disease (KD) is a complex acquired condition characterized by systemic blood vessel inflammation that primarily affects children under five years of age. It is clinically diagnosed as a syndrome, making it susceptible to misdiagnoses. Severe complications such as myocardial damage and coronary artery abnormalities can be fatal; thus, early diagnosis is critical for preventing disease progression. Currently, no specific diagnostic test can distinguish KD from viral or bacterial infections. Additionally, the molecular mechanisms underlying the disease remain unclear, hindering the development of targeted therapies. Objective: This study aimed to identify the genetic patterns and molecular mechanisms associated with …

Go to article

Soft Modular Robots: From Modular Tensegrity Structures To Bioinspired Sea Robots, Luyang Zhao May 2025

Soft Modular Robots: From Modular Tensegrity Structures To Bioinspired Sea Robots, Luyang Zhao

Dartmouth College Ph.D Dissertations

The rapid advancement of robotics necessitates systems capable of adapting to complex, unstructured environments. Soft robots, with their flexibility and compliance, excel in delicate interactions, making them ideal for medical applications and search-and-rescue missions. Modular robots, on the other hand, offer reconfigurability, enabling diverse task-specific adaptations in dynamic settings. Despite their individual advantages, the integration of soft and modular robotics remains underexplored. This proposal aims to develop soft modular robots that combine the adaptability of soft robotics with the versatility of modularity. These systems will be capable of autonomously transitioning between locomotion, manipulation, and infrastructure assembly across land, water, and …

Go to article

Real-Time System Availability For Cyber-Physical Systems, Jinwen Wang May 2025

Real-Time System Availability For Cyber-Physical Systems, Jinwen Wang

McKelvey School of Engineering Graduate Student Theses & Dissertations

Cyber-physical systems (CPSs), such as autonomous vehicles, are increasingly being deployed. The sensing, control, and actuation loop in CPSs must complete within strict timing constraints. Missing a real-time deadline can lead to catastrophic consequences, as CPSs continuously interact with the physical world. This highlights the importance of real-time system availability (i.e., timely execution) in CPS tasks, going beyond traditional security goals that primarily focus on confidentiality and integrity. From a security perspective, two factors affect real-time system availability. First, attackers with access to hardware resources in CPSs may disrupt the execution timing of real-time tasks. Second, the deployment of security …

Go to article

Improving The Reproducibility Of Deep Learning Software: An Initial Investigation Through A Case Study Analysis, Nikita Ravi, Abhinav Goel, James C. Davis, George K. Thiruvathukal May 2025

Improving The Reproducibility Of Deep Learning Software: An Initial Investigation Through A Case Study Analysis, Nikita Ravi, Abhinav Goel, James C. Davis, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns about reproducing the results of these deep learning methods. This is significant because reproducibility is the foundation of reliability and validity in software development, particularly in the rapidly evolving domain of deep learning. The difficulty of reproducibility may arise due to several reasons, including having differences from the original execution environment, incompatible software libraries, proprietary data and source code, lack of transparency, and the stochastic nature in some software. A study conducted by …

Go to article

Weak Formulation For Solving Inverse Problems In Reproducing Kernel Hilbert Spaces (With Applications To Learning Dynamical Systems), Victor William Rielly May 2025

Weak Formulation For Solving Inverse Problems In Reproducing Kernel Hilbert Spaces (With Applications To Learning Dynamical Systems), Victor William Rielly

Dissertations and Theses

We combine numerical and machine learning techniques to present a general framework for solving inverse problems using vector valued reproducing kernel Hilbert spaces in a variational formulation. We present this framework in two papers. In the first paper, we present an original state-of-the-art method derived in the context of our general framework for learning dynamical systems. In the second paper, we generalize the method from our first paper to arrive at the framework for solving inverse problems. Then we apply our general framework to the task of learning dynamical systems. In both papers we consider numerous applications of our methods …

Go to article

Improving User Retention And Learning Through Interactive Tutorial Systems, Prakhyat Chaube May 2025

Improving User Retention And Learning Through Interactive Tutorial Systems, Prakhyat Chaube

2025 Spring Honors Capstone Projects - Archive

The onboarding experience in software applications is crucial for user engagement and retention. Traditional static tutorials often fail to provide adaptive, role-specific learning, leading to user frustration and drop-off. This project introduces an interactive tutorial system tailored for students and tutors using the CSE Student Success Center App at the University of Texas at Arlington. Designed to enhance usability and accessibility, the system personalizes onboarding experiences through guided, role-based learning paths and real-time feedback. By streamlining the learning curve, the tutorial system fosters greater user confidence and engagement, ensuring a more intuitive transition into the application. User evaluations indicate a …

Go to article

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja May 2025

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Go to article

Modeling Literary Connections: Exploring Transregional Resistance In Dalit Poetry, Antara Bhattacharyay May 2025

Modeling Literary Connections: Exploring Transregional Resistance In Dalit Poetry, Antara Bhattacharyay

Mathematics, Statistics, and Computer Science Honors Projects

Structuring socio-political identities, the caste system (a graded form of hierarchy) remains entrenched in contemporary Indian society. Dalits, marginalized by the caste system, have expressed their resistance through literature, envisioning substantive equality and social change. In this thesis, I draw on digital humanities methods to examine regional variation in translated Dalit poetry from Bengali, Hindi/Urdu, Marathi, and Tamil languages. I utilize topic modeling—a machine learning algorithm that detects latent semantic structures in a text—as a point of departure for poetry analysis. I observe how topic modeling enables newer readings of the poems, revealing regionally resonant and broader Dalit themes.

Go to article

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja May 2025

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Go to article

Noninvasive Assessment Of The Tumor Using Cfdna, Irfan Alahi May 2025

Noninvasive Assessment Of The Tumor Using Cfdna, Irfan Alahi

McKelvey School of Engineering Graduate Student Theses & Dissertations

Next-generation high-throughput sequencing, which is increasingly generating vast amounts of genomic data, offers opportunities for a deeper understanding of the multifaceted nature of cancer and, hence, better patient care. However, the inherently complex and heterogeneous nature of cancer and the significant challenges in the generated data demand advanced data-driven frameworks to decode the molecular underpinnings of cancer. Moreover, the undeniable need for non-invasive approaches presents additional technical challenges in this domain. This dissertation proposes novel frameworks addressing three key challenges in computational oncology. The first study of this dissertation develops a data-driven algorithm to identify stemness signatures in metastatic castration-resistant …

Go to article

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja May 2025

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Go to article

First Prev Next Last