CS 598

Fall 2021 All Classes

All Classes

Special Topics

SHOW FINAL EXAM SCHEDULE

Credit: 2 TO 4 hours.

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites.

May be repeated in the same or separate terms if topics vary.

My Favorites

My Schedule

Section Status updates every 10 minutes.

CS 598 class schedule data for fall 2021
CRN	Type	Section	Time	Day	Location	Instructor	Section Details
62086	Lecture-Discussion	AK	12:30PM -1:45PM	WF	Siebel Center for Comp Sci	Kirlik, A	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Experimental HCI Section Info: Conceiving, designing, performing, analyzing data and reporting the results of experiments in HCI contexts and evaluating interactive technologies in engineering. Topics include defining the research question, selecting experimental objects, tasks, and participants, the ethical protection of subjects, selecting an experimental design, threats to validity, the collection and analysis of both qualitative and quantitative data, and reporting experimental research in publications. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
69375	Online	AO2	ARRANGED	n.a.	n.a.	Renear, A	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Foundations of Data Curation Section Info: This course is only for students that are in the online Computer Science MCS/MCS-DS Program. Additional ProctorU fees may apply. Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC or MCS:Computer Sci Online -UIUC.
54746	Lecture-Discussion	BAN	2:00PM -3:15PM	TR	Siebel Center for Comp Sci	Banerjee, A	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Deep Generative & Dynamic Mod. Section Info: Deep Generative and Dynamical Models Recent years have seen considerable advances in generative models, which learn distributions from data and also generate new data instances from the learned distribution; and dynamical models, which model systems with a dynamical or temporal component. Both of these developments have been leveraging advances in deep learning. The course will cover key advances in generative and dynamical models, including variational auto-encoders, normalizing flows, generative adversarial networks, neural differential equations, physics guided machine learning, among other topics. The course will be based on lectures, paper readings, presentations, and a course project. The course will assume the students have taken introductory courses in machine learning and deep learning equivalent to CS 446: Machine Learning and CS 498: Intro to Deep Learning. CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
66318	Online	CAC	9:30AM -10:45AM	MW	n.a.	Cobb, C	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Inclusive Cybersecurity & Priv Section Info: Cybersecurity and privacy solutions are often designed to address the needs of the majority. Increasingly, researchers have recognized that some people -- particularly those in vulnerable situations -- may have different security and privacy requirements and may experience greater harm if these requirements are not met. The course will include lectures, but it will be driven by student presentations of research papers. Additionally, students will complete course projects -- ideally, aligned with their existing research -- to put into practice the ideas covered in the readings. The course will assume only a basic prior understanding of security, privacy, and HCI; however, students with more expertise in these areas may get more out of their course projects. Prerequisite CS 225. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
46988	Lecture-Discussion	CM	9:30AM -10:45AM	TR	Siebel Center for Comp Sci	Mendis, C	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: ML for Compilers & Architect. Section Info: ML for compilers and architecture This course will explore how modern machine learning techniques are used in compilers and in computer architecture for systems decision making. We will first go through the basics of modern deep learning techniques including primers on different neural network architectures and the basics of sequential decision making. Then, we will cover how these techniques are used in the context of systems decision making including compiler optimizations, auto-tuning, performance modelling, performance aware neural architecture search, hardware systems design etc. We will go through recent papers on each topic to understand and to critically evaluate the latest developments in this space. This course will help prepare students for independent research in the covered topic areas. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
70734	Online	DEL	12:30PM -1:45PM	TR	n.a.	Delgosha, P	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Methods & Algor. in Lg. Graphs Section Info: Title: Mathematical Methods and Algorithms in Large Graphs Description: Many modern data arrives in a form that is best represented by combinatorial structures such as graphs, rather than classical time series. Graphs show up in various examples and applications, ranging from social networks and internet graphs to biological data. Modeling the interaction between objects as a graph allows us to better understand, analyze, and predict the behavior of such networks. Such understanding is crucial in subsequent applications, including but not limited to estimation, learning, data compression, and community detection. The focus of this course is to study mathematical tools to analyze graphs, specifically random graphs as models for large graphical data. We further employ this analysis to discuss several applications such as learning and compression. This is a graduate level course which is open to graduate students with a good level of mathematical maturity and a strong background in probability, as well as some basic background in graph theory. In this course, the students will develop skills in evaluating research papers and are expected to conduct a final research project. The class will be delivered online synchronously. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
40415	Lecture-Discussion	DWH	11:00AM -12:15PM	TR	Everitt Laboratory	Hoiem, D	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: 3D Vision Section Info: 3D Vision This is an advanced course that will cover the fundamental concepts and latest research in 3D vision, including SfM, stereo, MVS, SLAM, 3D surface fitting, texturing, single-view prediction and reconstruction, object and scene models, and novel view synthesis. There will be a mix of lectures, paper reading and review with small group discussion, programming assignments, and a final project. Prerequisite is graduate-level computer vision or research experience related to 3D vision, CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
43666	Lecture-Discussion	ECH	3:30PM -4:45PM	TR	Siebel Center for Comp Sci	Chandrasekharan, E	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Antisocial Computing Section Info: In this course, we will explore recent advances in detecting and discouraging antisocial behavior on the Internet. Focusing on a combination of sociological foundations and recent advances in HCI, NLP, and human-centered AI, we will examine online moderation through three lenses: understanding, building, and evaluating. First, we will survey the large spectrum of abusive behavior prevalent on the Internet and understand how current research defines such behavior. Next, we will examine existing moderation tools built using computational techniques and social computing theory. Finally, we will review experimental studies, surveys and real-time deployments that evaluate the efficacy of moderation strategies. Through this course, students will read and critique high-impact research papers, lead and engage in class discussions, provide and receive constructive peer-feedback, and execute a new research project for their final paper. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
46990	Lecture-Discussion	GDS	11:00AM -12:15PM	WF	Siebel Center for Comp Sci	Singh, G	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Logic and AI Section Info: For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Logic and Artificial Intelligence Given the black-box nature of the state-of-the-art AI models and the lack of associated formal guarantees, there is a growing interest in using formal methods for AI-based systems to ensure their reliability and interpretability. This direction is a key component of the so-called “Third wave of AI”. Similarly, there is a growing interest in leveraging data-driven machine learning for knowledge discovery and boosting logical inference. This course will introduce recent developments in both directions and outline several promising future research directions. Overall, the students will be exposed to the following topics: Training and querying with logic Verification of AI systems Robust training methods Machine learning for verification Programming by example Probabilistic circuits Symbolic explanations of neural networks Neurosymbolic computing Prerequisite CS 225. Basic background in artificial intelligence and formal logic is preferrable. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
72110	Lecture-Discussion	HAZ	2:00PM -3:15PM	WF	Siebel Center for Comp Sci	Zhao, H	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Transfer Learning Section Info: Transfer Learning While modern deep learning has achieved remarkable success in supervised learning, including image classification, speech recognition, machine translation, and game playing, this success crucially hinges on the assumption that the training data distribution (approximately) matches the test data distribution. This course will cover topics related to machine learning under the scenario where the training and test distributions are related, but not the same. We will study how to quantify the relatedness between distributions, tasks, and how the structure between them could be used to facilitate more efficient and effective learning. In particular, this course will cover the following topics, often from a representation learning perspective: domain adaptation/generalization, multitask learning, meta-learning, and adversarial robustness. Suggested Prerequisites: CS 225, and CS 446, Machine Learning or an equivalent introductory course on machine learning. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
63587	Online	HS	12:30PM -1:45PM	WF	n.a.	Sundaram, H	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Adv Social&Information Network Section Info: Topic: Advanced Social & Information Networks This is a deep dive into classic and recent, exciting results in network analysis, with particular emphasis on behavioral models. We shall discuss cascades, influence maximization, strategic behavior on networks, and mechanism deign. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
72124	Lecture-Discussion	KKH	11:00AM -12:15PM	MW	Electrical & Computer Eng Bldg	Hauser, K	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: ADV Comp. Topics in Robotics Section Info: Advanced computational topics in robotics A graduate survey course on robotics, focusing on mathematic foundations, algorithms, machine learning, and integrating software and hardware systems. Lecture topics will include physics simulation, collision checking, motion planning, probabilistic filtering and tracking, 3D perception, and robot learning. Students will read current academic papers and carry out a semester-long, team-based project. Special restrictions: no limits on CS and non-CS enrollment. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
43667	Online	MP	9:30AM -10:45AM	MW	n.a.	Parthasarathy, M	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Software Verification Section Info: CS598MP: Software Verification, Program Synthesis, and Interpretable AI Course website: https://courses.grainger.illinois.edu/cs598mp Though the formal title is “Software Verification”, this topics course will be on the intersection of software verification, program synthesis, and interpretable machine-learning. After a quick introduction to verifying software using mostly logic-based techniques and abstraction, we will use this as a basis to explore program synthesis and machine-learning of interpretable concepts. The topics on program synthesis and interpretable machine learning will include: - Program and expression synthesis o Exact learning from specifications (in particular, SyGuS) o Exact learning from input-output examples (programming by examples) o Learning from noisy examples - Learning logics o Logics that admit efficient learning (passive, online, one-class classification, active, etc.) o A general theorem of exact learning of logics o Learning logical expressions from noisy data using neural networks - Applications of learning logical expressions o Learning specifications for programs using online learning o Learning interpretable logical discriminators from visual images, video, etc. o Learning logics that represent programs The course will involve (a) reading and discussing papers, (b) presenting papers in this emerging area, and (b) working on projects, possibly in groups, where the goal is to have each project at the level of publication in a reasonably prominent conference. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for First Time Freshman students.
55918	Online	PPM	9:30AM -10:45AM	TR	n.a.	Rauchwerger, L	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Parallel Programming Models Section Info: Topic: Parallel programming with migratable objects. This course will teach and explore a method for parallel programming that can be used to program multicore desktop (with and without accelerators), small clusters, as well as petascale/exascale computers, with the same programming model. The model is based on the idea of over-decomposing the computation into a large number of interacting objects, mostly independent of the number of processors, and to empower an intelligent runtime system decide where and when the objects execute. Pre-requisite: No specific course requirements. Good sequential programming experience in C++ and/or Java. Prerequisite CS 225. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for NDEG:Computer Science Onl-UIUC, MCS:Computer Sci Online -UIUC, or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
70683	Online	PSO	ARRANGED	n.a.	n.a.	Liang, F	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Practical Statistical Learning Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC or MCS:Computer Sci Online -UIUC.
59671	Online Lecture	SG	9:30AM -10:50AM	TR	n.a.	Gupta, S	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Learning-Based Robotics Section Info: This course will introduce students to recent developments in the area of learning-based robotics. The course will start with an overview of background material from relevant subfields: computer vision, machine learning, robotics and control theory. Next, we will discuss advanced techniques for learning policies for robots, such as model-free reinforcement learning with function approximators, model learning, model-based RL with learned models, imitation learning, inverse reinforcement learning, self-supervised learning, exploration, and hierarchical reinforcement learning. These advanced techniques will be covered via recent research papers that develop and validate them. The course will conclude with case-studies on robotic navigation, and manipulation from recent papers. Project work as part of the course will provide a flavor of research in this new emerging area. Prerequisites: Understanding of basic concepts in artificial intelligence, and machine learning. Students must have taken at least one of the following courses: ECE 448 / CS 440 (Introduction to Artificial Intelligence), ECE 544NA (Pattern Recognition), ECE 549 / CS 543 (Computer Vision). For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
72357	Online Lecture	SGO	9:30AM -10:50AM	TR	n.a.	Gupta, S	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Learning-Based Robotics Section Info: This course will introduce students to recent developments in the area of learning-based robotics. The course will start with an overview of background material from relevant subfields: computer vision, machine learning, robotics and control theory. Next, we will discuss advanced techniques for learning policies for robots, such as model-free reinforcement learning with function approximators, model learning, model-based RL with learned models, imitation learning, inverse reinforcement learning, self-supervised learning, exploration, and hierarchical reinforcement learning. These advanced techniques will be covered via recent research papers that develop and validate them. The course will conclude with case-studies on robotic navigation, and manipulation from recent papers. Project work as part of the course will provide a flavor of research in this new emerging area. Prerequisites: Understanding of basic concepts in artificial intelligence, and machine learning. Students must have taken at least one of the following courses: ECE 448 / CS 440 (Introduction to Artificial Intelligence), ECE 544NA (Pattern Recognition), ECE 549 / CS 543 (Computer Vision). Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
57783	Online	SHW	2:00PM -3:15PM	WF	n.a.	Wang, S	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Adv. Top. in Robot Perception Section Info: Advanced topics in robot perception Perception is the ability to perceive, comprehend, and reason about the surrounding environment. Having a strong perception ability is crucial for autonomous robots to interact with the world. The goal of this course is to offer a holistic understanding of fundamentals and the latest trends in robot perception. We will cover various topics on sensing techniques, probabilistic state estimation, sensor fusion, 3D representations, and learning algorithms. We will also discuss several advanced topics in robot perception, such as perception in dynamic environments, open-world perception, embodiment, sim2real, and perception with provable guarantees. The format of this course will be a mix of lectures, seminar-style discussions, and student presentations. The course will be heavily discussion and project-oriented. Students will be responsible for paper readings, class participation, and completing a hands-on project. Prerequisite CS 225. Basic background in artificial intelligence and robotics is preferable. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
70199	Online	TMC	11:00AM -12:15PM	TR	n.a.	Chan, T	Part of Term: 1 Date Range: 08/23/21-12/08/21 Credit: 4 hours Section Title: Topics in Comp. Geometry Section Info: Topics in Computational Geometry This course will cover selected topics in computational geometry, which is concerned with efficient algorithms for solving problems involving geometric objects. Possible topics include geometric data structures (for example, for point location, range searching, and nearest neighbors), geometric optimization problems, geometric approximation algorithms, geometric streaming algorithms, and combinatorial geometry. The course will touch on some of the latest research results in the area. Prerequisite: CS 374 or equivalent For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.