Nov 25, 2024
Team Goals
Computational modeling and simulation have become prime discovery tools in the era of data-driven science and engineering. Mathematical models and computer simulations are used in virtually every scientific discipline – including climate modeling, materials research, biophysics, and health informatics. The complexity of these problems requires efficient algorithms that integrate multiscale models and multimodal data. This VIP team focuses on how Scientific Computing leverages algorithms and data to explain complex phenomena and discover novel solutions in science and engineering. The topics will be aligned with ongoing research projects in Computational Science and Materials Informatics (CoSMIc Lab)
Research Topics
- Multiscale Models and Algorithms for Complex Systems
- Machine Learning and Artificial Intelligence for Discovery and Design
- Scientific Software Development
- Workflows for Reproducible Data Analysis
Majors That Fit
Any major where scientific computing is relevant, including but not limited to
- Computer Science
- Data Science
- Mathematics
- Physics
- Materials Science
Skills in one or more of the following areas will be beneficial (not all are required – you can acquire more skills during the VIP!)
- Engineering Mathematics (Calculus, Linear Algebra, Statistics)
- Programming (Unix Shell, C/C++, FORTRAN, Python)
- Data Science (Scikit Learn, TensorFlow, PyTorch)
- AI/ML (Regression, Classification, Neural Networks)
Contact
Ulf Schiller
Sep 30, 2024
Team Concept
Advance the fields of computer science education and human-computer interaction by working on novel research/projects in the area’s of course/curriculum development, accessibility, learning sciences, feedback, assessment, intervention, UX design, and/or generative AI.
Team Goals
Drawing on theories of feedback, motivation, and self-regulation, and technology adoption, we aim to develop and research a dynamic, personalized feedback system able to aid students during moments of struggle. Additionally, we look to assist teachers in triaging and responding to student questions, reducing the administrative burden.
Research Topics
Computer Science Education, Automatic Feedback, Personalized Feedback, Learning Sciences, Digital Education, Human-Computer Interaction, Generative AI, Artificial Intelligence
Majors That Fit
Computer Science, Information Systems, Computer Engineering, Management Information Systems
Minors That Fit
Educational Technology
Contact
John Aromando, Computer & Information Science
Sep 17, 2024
Research Topics
Our team focuses on developing and integrating a deep reinforcement learning framework into real-world software challenges. In this project, students will learn about reinforcement learning and become familiar with specific reinforcement learning algorithms. They will also participate in the development of the reinforcement learning framework by implementing new features or fixing existing bugs. Additionally, students will work on integrating the implemented algorithms into real-world software systems and observe/benchmark performance improvements.
Majors Preparation and Interests
Students should have a background in Python and data structures. Knowledge of machine learning and reinforcement learning is encouraged but not required.
Goal
The team aims to explore data intelligence systems by integrating machine learning, particularly deep reinforcement learning, into data structure design, data system optimization, and workload analysis.
Faculty
Team Mentor: Dong Dai
Sep 9, 2024
Code to Scale
Research Issues
Learning and using directives for parallel platforms; Migrating legacy code to GPUs and co-processors using high-level parallel programming models; Parallelizing irregular algorithms on massively parallel processors; Exploring Repeatability and Reproducibility issues.
Research Areas
Programming models, benchmarking, software and tools, performance analysis, profiling, compiler/runtime, memory optimization, interdisciplinary science, reproducibility
Skills
Programming Models such as OpenMP, OpenACC, MPI, Julia, Python among others, Compiler, Computing, AI, Large Language Models (LLM)
Majors Preparation and Interests
- CS: AI, machine learning, parallel programming, computer architecture
- CE: computer hardware, AI security, AI acceleration
Any major where students are interested in computational science would benefit from VIP-HPC
Projects
- Benchmarking HPC applications on large HPC systems
- Benchmarking MLPerf applications on large HPC systems
- Explore applicability of programming models on HPC projects
- Exploring energy efficiency and power consumption for HPC applications
- Exploring energy efficiency and power consumption of AI models
- Automating writing of tests for programming models, using LLMs
Key Elements
High Performance Computing, Parallel Computing, Parallel Programming Models, Hardware Architectures, Portability, Scalability, Performance, Repeatability and Reproducibility.
Goals
High Performance Computing is a field that enables scientific advancement of real-world applications by effectively utilizing computing resources with the help of software and tools. The goal of this VIP team is to build the next generation workforce on high performance computing, training them on hpc, software engineering skills and help them apply the skills learnt on problems.
Results
Matt Stack, Paul Macklin, Robert Searles, Sunita Chandrasekaran, Jeffrey C. Carver, and Karla Morris. 2022. OpenACC Acceleration of an Agent-Based Biological Simulation Framework. Computing in Science and Engg. 24, 5 (Sept.-Oct. 2022), 53–63.
Wright, E., Ferrato, M. H., Bryer, A. J., Searles, R., Perilla, J. R., & Chandrasekaran, S. (2020). Accelerating prediction of chemical shift of protein structures on GPUs: Using OpenACC. PLoS computational biology, 16(5), e1007877.
Munley, Christian, Aaron Jarmusch, and Sunita Chandrasekaran. “LLM4VV: Developing LLM-driven testsuite for compiler validation.” Future Generation Computer Systems (FGCS) Volume 160, November 2024, Pages 1-13 (2024).
Faculty
Sunita Chandrasekaran, Phd, CISC, schandra@udel.edu
Stephen Siegel, Phd, CISC
Rudolf Eigenmann, Phd, Professor, ECE, eigenman@udel.edu
Aug 26, 2024
Team Goals:
Housed within the Sensify Lab, Computing for Social Good focuses on exploring the application of computer science, human-computer interaction, and ubiquitous computing principles to high-value social problems. Teams aim to engineer cyber-physical and software systems that extend user capabilities, within areas like education, health & wellbeing, and environmental sustainability. The overarching goal is to create technological advancements and nurture a community of innovators equipped to positively impact society through the intersection of human-centered design and experiential learning.
Research Topics:
While not exhaustive, VIP students are often able to work on various related projects in the lab:
- Online News and Misinformation Detection and Mitigation
- Emotional Predictions for Productivity and Wellbeing Support
- Advancing Collection and Insight Generation from Online Social Media Data
- Leveraging Interaction Data to Support Adaptive Listening
Majors That Fit:
Computer Science, Mechanical Engineering, Computer Engineering, Electrical Engineering, Human-Computer Interaction, Design, Psychology
Contact:
Matthew Mauriello
Email: mlm@udel.edu
Oct 30, 2023
Research Topics
Trustworthy AI research focuses on creating transparent, accountable, and reliable artificial intelligence systems. It includes two critical aspects: (1) eXplainable AI (XAI), which aims to make AI decisions understandable and free from bias. (2) Robust Machine Learning, which ensures AI systems can handle unforeseen conditions and adversarial attacks. The VIP team will apply the two aspects of Trustworthy AI to various scientific applications.
Projects
- Weather nowcasting and forecasting.
- Analyze historical weather data and develop time series predictive models for short-term and long-term weather prediction.
- Underwater geo-acoustic data analysis for marine life identification.
- Train computer vision models to detect and classify marine life species using sonar images.
- Flood water segmentation and interpretation using satellite images.
- Fine-tune large pre-trained models (LPMs) to segment and interpret flood water using satellite images.
Majors and Interests
- CS: AI, machine learning, deep neural networks, computer vision
- CE: computer hardware, AI security, AI acceleration
- EE: signal processing, remote sensing
- Math: algorithms, ML
Contact
Xi Peng, CIS, xipeng@udel.edu
