Special Topics Course

This graduate course gives an overview of machine learning for planning and control of complex dynamical systems. Topics include reinforcement learning in continuous state/action spaces, data-driven dynamics models, imitation learning, online policy optimization, and robustness/adaptivity to environment shifts. Students will develop a thorough understanding of fundamental algorithms and learn to select appropriate methods based on the problem's interaction and information protocols.

This class is a hands-on class on vulnerability analysis that uses security exercises as a basis for education and training. Students will be required to solve medium-to-complex security problems during class. The problems require an understanding of operating system concepts, as well as the basics of computer security. 

Course pre-requisities: CMPSC 170 and CMPSC 177. Once the quarter starts, instructor approval is required to maintain enrollment in the course, including if students do not have the listed pre-requisite courses completed. 

This graduate course offers an in-depth exploration of foundational academic papers in the field of computer security. Each week, students will engage with seminal research that has shaped our understanding of security challenges and that introduced innovative solutions. The course is organized around weekly themes, with papers selected to highlight interesting insights and advancements. Each session will begin with an introduction where I will contextualize the papers within the evolution of computer security. Then, students will present papers and we discuss and critically review them.

Networks are a natural way to represent a variety of interacting complex systems - from disease spreading and brain networks, to social networks and political networks.

In this course, we will study the foundations of networks and investigate how the structure of networks affects the spread of signals on the network. Next, we will learn about the geometry and topology of networks, and topological data analysis on networks. Finally, we will learn about graph neural networks and the interface between network properties and learning. This course contains a project. 

To create innovative AI-supported systems that truly benefit end-users in real-life situations, it is crucial to focus on the interactive and real-time user experience of AI. This course is centered around investigating the various aspects of human-AI systems, including interface design, user agency, explainability, ethics, and the human-centered design process involving AI. We will examine these through reading research papers and through the design and prototyping of an AI Task Guidance System.

Mixed and Augmented Reality, now often subsumed under the overarching term XR: Extended Reality, has been an active research field since the 1990s. It has recently gained significant popularity because of the possibility of being implemented on smartphones, because of new emerging head-worn platforms (including the recent Apple "VisionPro" device), and because of its unique approach of offering context-based computing directly in a person's field of vision. Augmented Reality is the concept of overlaying computer-generated information on top of the physical world.

This course explores advanced topics in highly scalable Internet services and their underlying systems’ architecture. Software today is primarily delivered as a service: accessible globally via web browsers and mobile applications, and backed by millions of servers.

This course covers advanced topics on information retrieval systems and neural ranking algorithms. The content to be focused includes retrieval,  ranking, indexing, and online support for large-scale search services. Recent papers in top conferences on neural information retrieval will be reviewed, and issues in relevance, efficiency, and scalability will be studied.
 

Are blockchains real? There’s a lot of excitement about blockchains and cryptocurrencies mixed with a lot of skepticism and pessimism. One thing is clear, the field instigated tremendous advances to the foundations of distributed systems and applied cryptography. This course will overview key advances in blockchains with a focus on the scientific foundations underpinning them.

This course will focus on learning problems for networking, i.e., how network protocols or network operators make their decisions at different granularities (e.g., network, TCP, application, etc.) to keep networks safe and performant. How these decisions are made right now, and how one can replace existing heuristics-based decision-making with ML-based learning models. We will learn about the challenges of applying machine learning to learning problems in networking and how we can resolve them.