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.
- 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
Xi Peng, CIS, firstname.lastname@example.org
Goals of This Team
Autonomous driving is an innovative technology that allows vehicles to navigate and perform driving tasks without human intervention. This VIP team is dedicated to the research and development of cutting-edge solutions for autonomous driving. This team will build and design autonomous driving prototyping systems for safety and efficiency.
- CS: DNNs, computer vision, real-time OS, ROS
- ME: robotics, planning, control, CAN bus
- EE: sensing, signal processing, DSRC/C-V2X
- CE: computer architecture, cybersecurity
- Multi-sensor fusion techniques;
- Heterogeneous hardware architecture;
- Digital twin simulation environment;
- Connected and autonomous driving;
- Energy efficient autonomous driving;
- Cybersecurity for connected and autonomous driving vehicle.
Deep neural networks, robot operating system, sensing, perception, planning, control, embedded devices, vehicular communications, heterogeneous accelerator, real-time operating system
Goals of this Team
ALGORITHMS are an essential component of modern computing and have become increasingly important as the amount of data generated by businesses, governments, and individuals has grown exponentially. This VIP team centers on the study of algorithms, consisting of two threads:
- Programming Contest Thread. Participating in programming contests can have several benefits: improving problem solving skills, enhancing programing skills, providing network opportunities, and enhancing career prospects. This thread serves as a channel for students who are interested in participating programming contest. With the support from the Computer and Information Science Department at UD, team members in this thread will collectively learn programming fundamentals, design contest strategies, participate in mock programming contests, and finally, patriciate in programming contests in the US.
- Research Thread. Algorithm research involves the study of algorithms, their properties, and their applications. The team in this thread will explore research topics in combinatorial optimization and social network analysis, in collaboration with the Computational Data Science Lab at UD (https://udel.edu/~amotong/).
Any major that involves coding and algorithms will fit, including but not limited to
- Computer Science
- Computer Engineering
- Electrical Engineering
- Data Science
- Mathematics …
- Meeting with students who have passion in programming and algorithms
- Practicing coding interview questions
- Improving algorithm design skills
- Having fun in mock programming contest
- Possibly, winning or placing highly in programming contests…
- Acquiring research experience in computer science
- Solving research-level algorithmic problems
- Implementing complex algorithms and contributing open-source project
- Publishing research papers
- Receiving summer internship offers from the Computational Data Science Lab at UD.…
Greg Silber, Professor, CIS, email@example.com
Guangmo Tong, Professor, CIS, firstname.lastname@example.org
Tools for Terrific Teaching
How do we create/evaluate/revise automatic feedback? How do we make teaching manageable? How do we make learning to program better/easier/funner? How do we predict/support students’ performance using learning analytics? How do we reduce racial/gender/financial/etc. inequality in the world?
Fall 2022: View potential ideas.
Digital Education, Automatic Feedback, Programming Languages, Human-Computer Interaction, Educational Games, Computer Science Education
Majors Preparation and Interests
Computer Science Educational Technology Instructional Design Game Studies
Educational software and APIs. Tools for LMSes. Educational games. Learning analytics and Data Science. Instructional Design.
Measurably improve learning. Increase student engagement. Make professors jobs easier. Improve the world.
Austin Cory Bart, PhD Computer Science, Assistant Professor, Computer Science, email@example.com
Code to Scale
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.
Parallel Algorithms, Embedded Computing, GPUs FPGAs DSPs, Quantum Chemistry, Next-Gen Sequencing
Majors Preparation and Interests
ECE, CIS, CBE, BME, Chemistry and Biochemistry – Parallel Algorithms, Computer Architecture, Parallel Programming Models, Embedded Computing, GPUs, FPGAs, DSPs, Molecular Dynamics, Quantum Chemistry, Next-Gen Sequencing
High Performance Computing, Parallel Computing, Parallel Programming Models, Hardware Architectures, Portability, Scalability, Performance, Repeatability and Reproducibility.
Compute nodes pose thousand-way parallelism between parts of application, such as task parallelism, process-level and thread-level parallelism within a process and a core, along with hardware multithreading, instruction-level parallelism and pipelining of instructions. We see that technological advances have been instrumental in all scientific domains, be it astrophysics, medicine, finance and so on. However a major concern is if legacy code can tap into the massive potential of hardware resources; there is a real challenge to extract these parallelism. Moreover these codes are highly science-driven with varying workloads that demand dynamic load balancing and locality-aware scheduling. Modernizing legacy applications consisting of hundreds and thousands of lines of code for current and emerging architectures is a real challenge. This project aims to explore and create prototypes for parallelizing algorithms on heterogeneous platforms consisting of CPUs along with GPUs and Co-processors. Other hardware platforms of interest would be reconfigurable hardware such as FPGAs and specialized accelerators such as DSPs. However one of the primary challenges with the advances has been to understand how scientific applications were ported to hardware platforms using low-level or proprietary language – these are tied too close to the hardware. This project will explore ways to migrate such programs to a higher-level directive based programming model with a goal that in the process, a portable code be maintained. The overachieving goal is to write once and reuse multiple times such that less time is spent on programming and more time is spent on the science itself. This project will expose the students to large supercomputers comprising over 1 Million cores along with latest generation Co-Processors and several hundreds and thousands of GPUs.
Sunita Chandrasekaran, Phd, CISC, firstname.lastname@example.org
Stephen Siegel, Phd, CISC
Rudolf Eigenmann, Phd, Professor, ECE, email@example.com