Training Program Syllabus


Instructors


  • Dr. Houbing Song, Department of Information Systems, UMBC
  • Dr. Jiawei Yuan, Department of Computer and Information Science, UMass Dartmouth

TAs


  • Mengjie Jia, Graduate Student, Department of Computer and Information Science, UMass Dartmouth
  • Wenkai Tan, Graduate Student, Department of Information Systems, UMBC
  • Safayat Bin Hakim, Graduate Student, Department of Information Systems, UMBC
  • Kamal Acharya, Graduate Student, Department of Information Systems, UMBC
  • Varun Magotra, Graduate Student, Department of Information Systems, UMBC

Training Description


This graduate-level course for students in three disciplines (Computing, Mathematics, and Physics) to foster multidisciplinary research and education using advanced cyberinfrastructure (CI) resources and techniques. The course will teach students how to apply knowledge and skills of high-performance computing (HPC) and Big Data to solve challenges in Atmospheric Sciences. We focus on the application area of atmospheric physics and within its radiative transfer in clouds and global climate modeling, since these topics are important, pose computational challenges, and offer opportunities for big data techniques to demonstrate their impacts. The participants in the new initiative will be selected competitively to form multidisciplinary teams of three participants with one participant from each area. The material is at the level of an advanced graduate course. All work is conducted in a multidisciplinary team with participants from each area, mentored by a faculty and supported by a teaching assistants (TA) from each area. In the first 10 modules consisting of instruction in all three areas, team building is achieved by homework. In the final 5 modules, each team applies the material learned immediately to a small research project, culminating in a technical report and a project presentation.

Academic Integrity


By enrolling in this training, each participant assumes the responsibilities of an active participant in scholarly community in which everyone's academic work and behavior are held to the highest standards of honesty. Cheating, fabrication, plagiarism, and helping others to commit these acts are all forms of academic dishonesty, and they are wrong. Academic misconduct could result in disciplinary action that may include, but is not limited to, suspension or dismissal of your training.

Tentative Training Structure (subject to change)


Module Topic
0 Online communication testing and introduction.
1 Introduction of Deep Learning, Linux, and GPU server environment.
2 More about deep learning.
3 AI infrastructure and deep learning hands-on modules deployment, setup, configuration.
4 Advance resource management in cyberinfrastructure.
5-6 Bridging AI techniques to operational cybersecurity challenge. Participants will learn how to identify problems suitable for AI techniques and apply introductory solutions to solve them. Topics can be selected according to your background, such as
  • Malware detection
  • Software vulnerability detection
  • Network intrusion detection
  • Scam/fraud detection
  • UAV anomaly detection
7-9 Advanced hands-on training towards sophisticated operational cybersecurity challenges.
10-11 Final Project: identification, application, customization, and evaluation of AI/Machine techniques to a given operational cybersecurity challenge.
12 Project presentation.