CS 598

Spring 2025 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 spring 2025
CRN	Type	Section	Time	Day	Location	Instructor	Section Details
61852	Lecture-Discussion	APE	2:00PM -3:15PM	WF	0220 Siebel Center for Comp Sci	Moses, W	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Advanced Perform Engineering Section Info: Title: Designing and Building Applications for Extreme Scale Systems Learn how to design and implement applications for extreme scale systems, including analyzing and understanding the performance of applications, the primary causes of poor performance and scalability, and how both the choice of algorithm and programming system impact achievable performance. The course covers multi-and many-core processors, interconnects in HPC systems, parallel I/O, and the impact of faults on program and algorithm design. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
69012	Lecture-Discussion	APK	11:00AM -12:15PM	TR	106B3 Engineering Hall	Kloeckner, A	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Lang & Abstractions for HPC Section Info: Languages and Abstractions for High-Performance Scientific Computing. This practically-oriented class considers programming language tooling for the construction of high-performance numerically-based software targeting distributed-memory GPU and wide-vector multi-core machines. Topics covered include: Machine Abstractions and Hardware Realities, Kernels and the Anatomy of High-Performance Code, Measuring and Understanding Performance (Types of measurements, performance counters and derived quantities, instrumentation and measurement error), Construction and Design of Domain-Specific Languages (array and scalar languages, parallel primitives, intermediate representations, metaprogramming), Translation and Compilation Techniques (symbolic manipulation, interfacing with computer algebra, kernel fusion, polyhedral representation and transformation), Code Generation and Just-in-Time Compilation, Performance Modeling and Tuning. Prerequisites: Knowledge of C and Python, interest in numerical applications, prior exposure to GPU programming and elementary compiler concepts. 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.
48248	Lecture-Discussion	CAG	11:00AM -12:15PM	TR	1214 Siebel Center for Comp Sci	Gunter, C	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Sec and Priv for IoT in Homes Section Info: Topic: The Internet of Things (IoT) provides connectivity of sensors and actuators using packet networking. This course considers the development of IoT in homes with particular attention to threats to security and privacy. Students will gain familiarity with the relevant research literature and develop a research project. Pre-requisites: knowledge of computer security and privacy. 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 OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
48269	Lecture	DGM	11:00AM -12:15PM	TR	0216 Siebel Center for Comp Sci	Banerjee, A	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Deep Generative Models Section Info: 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, diffusion models, neural differential equations, learning operators, among other topics. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
43732	Online	DLH	ARRANGED	n.a.	n.a.	Sun, J	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Deep Lrng for Healthcare Section Info: Welcome to the Deep Learning for Healthcare course! In this course, we will explore deep learning (DL) methods and their applications in healthcare. The course will include video lectures, self-guided labs, and homework assignments. During this time, you will learn about different DL and health applications topics, and develop practical experience in building deep learning models using healthcare data. Additionally, you will learn how to use "pyhealth," a package specifically designed for healthcare AI tasks. We encourage you to use pyhealth for your final project and, if possible, contribute to its improvement. In the second half of the course will be a group project where you will work together to understand, replicate, and extend a recently published work in deep learning for healthcare. This project will give you hands-on experience in applying DL methods to real-world healthcare problems. To assess your understanding of the course material, we will have a midterm exam before the spring break. We hope you enjoy the course and learn a lot about deep learning and its applications in healthcare!. Course Objectives Upon completion of this course, you will be able to: 1. Understand and apply various deep learning models, including deep neural networks, convolutional neural networks, recurrent neural networks, autoencoders, attention models, graph neural networks, and deep generative learning. 2. Identify and implement different healthcare applications using DL methods, such as clinical predictive models, computational phenotyping, patient risk stratification, treatment recommendation, clinical natural language processing, and medical imaging analysis. 3. Develop practical experience in implementing various deep learning models on diverse medical data, using popular deep learning frameworks like PyTorch and data science software like Jupyter Notebook. 4. Gain hands-on experience in data preprocessing, data visualization, and model interpretation for healthcare applications. 5. Develop skills in critically evaluating and selecting appropriate DL models for healthcare applications. By the end of this course, you will have a comprehensive understanding of deep learning methods and their applications in healthcare, as well as practical experience in implementing DL models using popular frameworks and tools. You will be well-prepared to work on real-world healthcare projects that involve DL and contribute to the development of innovative healthcare solutions. Prerequisites Basic machine learning knowledge is helpful but not strictly required.* Strong programming skills in Python are required. A fair understanding of linear algebra and calculus is required. Sufficient system knowledge, such as using Linux and setting up programming environments on the cloud, is required. No knowledge in healthcare domain is required. This course is only for students that are in the Computer Science MCS-DS Program. Additional ProctorU fees may apply. Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
65866	Online	DSO	ARRANGED	n.a.	n.a.	Park, T	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Advanced Bayesian Modeling Section Info: This section is only for students that are in the Computer Science Online MCS/MCS-DS Program offered on the Coursera platform. Additional ProctorU fees may apply. Restriction(s): Restricted to Graduate - Urbana-Champaign. Restricted to MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC.
60197	Lecture-Discussion	FAL	12:30PM -1:45PM	WF	0216 Siebel Center for Comp Sci	Lai, F	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Systems for GenAI Section Info: This course will introduce the key concepts and the state-of-the-art in practical, scalable, and fault-tolerant software systems for emerging Generative AI (GenAI). It will encourage you to design system tools or apply existing ones in your own research. Topics cover basics of GenAI models from a systems perspective; systems for GenAI lifecycle (pre-training, training, fine-tuning/alignment, inference serving, and grounding); etc. The course will be a mix of lectures, student presentations, seminar-style discussions, and a semester-long project on GenAI topics. Prerequisite: This course is NOT focused on AI methods but on building software systems to support AI methods in practice. Students are expected to have good programming skills and must have taken at least one undergraduate-level systems-related course (from operating systems, databases, distributed systems, or networking). Having an undergraduate ML/AI course is helpful but not required. 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 OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
46428	Lecture-Discussion	FTS	2:00PM -3:15PM	TR	1035 Campus Instructional Facility	Ganesan, A	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Fault-Tol Consistent Data Sys Section Info: How are distributed systems built in the modern data center? How do hardware trends impact system design? How do we rethink decades-old protocols and ideas for the modern data center? If you are curious about answers to these questions, this course is for you. This course will dive deep into replication and consensus protocols, geo-replicated systems, distributed transactions, and various consistency models and how to implement them. We will also learn how traditional distributed protocols have been rearchitected for emerging hardware such as persistent memory, RDMA, and programmable switches and NICs. We will also discuss case studies from production systems. Pre-requisites: Operating Systems (CS 423) or Distributed Systems (CS 425) 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
77266	Lecture	GAA	2:00PM -3:15PM	MW	1214 Siebel Center for Comp Sci	Har-Peled, S	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Geometric Approx Algorithms Section Info: Geometric Approximation Algorithms. This course will cover some basic algorithms in geometric approximation algorithms, from grids, quadtrees, well-separated pairs decomposition, coresets, LSH, proximity search, and similar topics. Prerequisite: CS 473 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
59156	Lecture-Discussion	GBL	9:30AM -10:45AM	MW	0220 Siebel Center for Comp Sci	Liu, G	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Gen Mod for BioMed & Life Sci Section Info: Generative models for biomedicine and life sciences. Generative models have greatly advanced the field of biological sciences and medicine, enabling atomic level design and modeling of molecular systems such as protein, DNA and small molecules. In this course, we will discuss recent advances in generative AI for biomedicine, with special focus on geometric aware deep learning, multimodal diffusion and flow matching on diverse data manifolds, as well as foundational models for biomedicine and life sciences applications such as protein design, drug discovery, and understanding functions and dynamics of complex biomolecular systems. This will be a graduate level course in seminar format. Prerequisite: Introduction to 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
39664	Lecture-Discussion	GCK	2:00PM -3:15PM	TR	0220 Siebel Center for Comp Sci	Chacko, G Warnow, T	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Methods & Applic in Net Analys Section Info: This course is centered around the concepts of community detection and search, analysis of large networks, development of realistic network simulators, network growth models, and evaluation techniques. Emphasis is placed on real-world problems in the general area of scientometrics. There are three components to the course. a) Assignments b) Lectures c) Projects. Grades are assigned based on satisfactory completion of assignments, required class presentations, participation in class discussions, and assessed quality of course projects.. A successfully completed course project should be "near-ready" for submission to a conference or journal. Students are strongly encouraged to publish results from these projects and the instructors will work with students to support manuscript submission. Participating students will explore scientific questions, analyze data, develop new methods or apply existing ones. The course is taught by George Chacko and Tandy Warnow. It is designed for graduate students in computer science. Students from other disciplines are welcome but must have approval from an instructor. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
62182	Lecture-Discussion	GMA	9:30AM -10:45AM	MW	1214 Siebel Center for Comp Sci	Kim, M	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Generative Models for Audio Section Info: This course explores generative models widely used in speech, music, and audio processing. Beginning with foundational concepts like linear predictive models, autoregressive models, and state-space models such as Hidden Markov Models, the course builds a strong understanding of traditional audio signal processing techniques. Building on these basics, students will delve into modern deep learning-based generative models, examining key approaches such as adversarial learning, controlled latent spaces, recurrent models, diffusion models, and others. The course emphasizes comparative analysis to highlight the unique characteristics of each model. Students will also engage in presentation sessions, critically reviewing and discussing key literature in audio generation. Students are expected to know the basics of DSP and machine learning. Hands-on experiences and knowledge of deep learning projects are also strongly recommended. Prerequisite: CS 545. 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 OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
43808	Lecture-Discussion	JGE	3:30PM -4:45PM	TR	3038 Campus Instructional Facility	Erickson, J	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Advanced Data Structures Section Info: Topic: Advanced Data Structures This course will survey important developments in data structures that go beyond the typical undergraduate computer science curriculum. Potential topics include: balanced search trees, priority queues (e.g., Fibonacci heaps), amortized analysis, the union-find problem, hashing, geometric data structures (e.g., range searching), approximate nearest neighbor search (e.g., locality-sensitive hashing), bit-packing techniques (e.g., fusion trees and succinct data structures), persistent data structures, dynamic graph algorithms (e.g., dynamic connectivity and shortest paths), distance oracles, strings and text indexing (e.g., suffix trees), I/O-efficient data structures, and (conditional) lower bounds. The precise topics will depend on the interests and background of the course participants. Prerequisites: Students in all areas of computer science and related disciplines are welcome, including algorithmically mature undergraduates. An undergraduate algorithms course at the level of CS 473 is a prerequisite; however, specific background material will be introduced as needed. 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
68136	Lecture-Discussion	JY2	3:30PM -4:45PM	TR	1304 Siebel Center for Comp Sci	You, J	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Topics in LLM Agents Section Info: This course offers an in-depth exploration of the fascinating field of LLM agents. Designed as a seminar-style course, it guides students through the fundamental methods that power LLM agents and examines their practical applications in real-world contexts. We begin with an introduction to the core concepts of LLM agents, then delve into the latest research on building agents, covering topics such as memory, planning, reasoning, and more. We will also explore the interface between LLM agents and their environments, including areas like retrieval-augmented generation and tool learning. Finally, we will examine impactful applications of LLM agents, with ample opportunities for collaborative brainstorming sessions. The course is structured around reading cutting-edge research papers, student-led presentations, interactive discussions, and collaborative semester-long projects. This approach aims to foster a deep understanding of latest LLM agent research and equip students with skills to contribute the research in relevant fields. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for NDEG:Computer Science Onl-UIUC, MCS: Computer Sci OFF - UIUC, or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
43782	Lecture-Discussion	KCC	2:00PM -3:15PM	TR	1304 Siebel Center for Comp Sci	Chang, K	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Using LLMs AKA ChatGPT Section Info: Understanding and Using Large Language Models AKA ChatGPT - Building Autonomous Agents for Knowledge Acquisition. Generative AI has transformed NLP and established a new paradigm upon large language models (LLMs) for building autonomous agents that can interact, acquire, and process knowledge for humans. While LLMs like ChatGPT have created real buzz, our understanding of these large and complex models is limited: How does it work? What can it do? Can we use LLMs to automate daily tasks of knowledge acquisition, such as reading technical papers, browsing websites, and checking emails? This class will take a laboratory and collaborative approach to learn LLMs by surveying the literature and doing research: For “understanding”- We will characterize the behavior of LLMs. For “using”: We will program LLMs as software agents that can execute these tasks on behalf of users. Objective: Publishable survey/research papers. Format: Hands-on survey and research in small groups of 1-2 leads and 1-2 apprentices. Prerequisites: 1) Lead- Research experience in NLP/ML/DM (having published in ACL/EMNLP or similar venues) and 2) Collaborator/Apprentice: CS447 and strong CS background. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, MCS: Computer Sci OFF - UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
62819	Online	LHO	ARRANGED	n.a.	n.a.	Sun, J	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Deep Learning For Healthcare Section Info: Welcome to the Deep Learning for Healthcare course! In this course, we will explore deep learning (DL) methods and their applications in healthcare. The course will include video lectures, self-guided labs, and homework assignments. During this time, you will learn about different DL and health applications topics, and develop practical experience in building deep learning models using healthcare data. Additionally, you will learn how to use "pyhealth," a package specifically designed for healthcare AI tasks. We encourage you to use pyhealth for your final project and, if possible, contribute to its improvement. In the second half of the course will be a group project where you will work together to understand, replicate, and extend a recently published work in deep learning for healthcare. This project will give you hands-on experience in applying DL methods to real-world healthcare problems. To assess your understanding of the course material, we will have a midterm exam before the spring break. We hope you enjoy the course and learn a lot about deep learning and its applications in healthcare!. Course Objectives Upon completion of this course, you will be able to: 1. Understand and apply various deep learning models, including deep neural networks, convolutional neural networks, recurrent neural networks, autoencoders, attention models, graph neural networks, and deep generative learning. 2. Identify and implement different healthcare applications using DL methods, such as clinical predictive models, computational phenotyping, patient risk stratification, treatment recommendation, clinical natural language processing, and medical imaging analysis. 3. Develop practical experience in implementing various deep learning models on diverse medical data, using popular deep learning frameworks like PyTorch and data science software like Jupyter Notebook. 4. Gain hands-on experience in data preprocessing, data visualization, and model interpretation for healthcare applications. 5. Develop skills in critically evaluating and selecting appropriate DL models for healthcare applications. By the end of this course, you will have a comprehensive understanding of deep learning methods and their applications in healthcare, as well as practical experience in implementing DL models using popular frameworks and tools. You will be well-prepared to work on real-world healthcare projects that involve DL and contribute to the development of innovative healthcare solutions. Prerequisites Basic machine learning knowledge is helpful but not strictly required.* Strong programming skills in Python are required. A fair understanding of linear algebra and calculus is required. Sufficient system knowledge, such as using Linux and setting up programming environments on the cloud, is required. No knowledge in healthcare domain is required. Online MCS students should select section DLH. This is the on-campus section for Chicago MCS and Urbana students. 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 or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
40659	Lecture-Discussion	LMZ	9:30AM -10:45AM	TR	4039 Campus Instructional Facility	Zhang, L	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Software QA w Generative AI Section Info: Modern Large Language Models (LLMs) like ChatGPT have demonstrated remarkable capabilities across diverse fields, notably in natural language processing and programming. In this course, we will together explore the impact of such advanced generative AI techniques on the important area of software quality assurance. This course will dive deep into the intersection of generative AI and software quality assurance, illustrating how these technologies can be synergistically combined to elevate software reliability, robustness, and correctness. We will cover a range of interesting topics, including foundational principles and cutting-edge research on software quality assurance, recent representative LLMs for code, emerging techniques on leveraging LLMs for software quality assurance, as well as innovative methods targeting quality assurance of LLMs themselves. There is a possibility that this course may need to move to an online zoom format during the semester, however access to the classroom for this will remain intact for students to participate in zoom. 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.
65627	Lecture-Discussion	PEN	11:00AM -12:15PM	TR	1304 Siebel Center for Comp Sci	Peng, H	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: LLM Post-pretraining Section Info: Recent progress in open-source pretrained large language models (LLMs) have opened up new exciting opportunities for researchers to explore creative ideas, even when they may lack extensive resources for pretraining. This course delves into them through lectures and student-led discussions. We will cover continual pretraining, instruction fine-tuning, preference learning, alignment, efficiency optimization, evaluation, and so on. Though this course is primarily designed for graduate students, motivated undergraduates with suitable backgrounds are also welcome. Prior research experience in related fields (such as natural language processing, machine learning, vision, etc.), strong skills for paper reading and presentation, proficiency in Python and modern deep learning frameworks are assumed. 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
56938	Lecture-Discussion	PPM	12:30PM -1:45PM	TR	0220 Siebel Center for Comp Sci	Rauchwerger, L	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Parallel Programming Models Section Info: Title: Parallel Programming Models for Portable High Performance Computing Portable High Performance Computing means portable performance in time and space. In other words, the performance of programs requiring HPC (resource intensive codes) need to be portable across the main existing architectures and across the machines that will be developed in time. In order not to have to rewrite entire applications to port them across systems we raise the level of abstraction at which programs are written and leave the 'details" of mapping the application onto the architecture to the vendors themselves. One way to achieve portable performance of applications and ease of programming effort is to use a hierarchical system of generic and domain specific libraries. In this course we will present several high level libraries and languages that can be built on top of the existing software development infrastructure, i.e. do not require new compilers, debuggers, etc. performance Libraries have to implement parallel algorithms and programs without requiring the user to deal with the complexities of parallel program execution on a parallel architecture. In this course we first present the state of the art in parallel programming models. Then we will present the latest approaches to parallel library design and how they alleviate the performance portability and ease of use problems. We will cover generic libraries such as TBB, STAPL, Cilk++ and then spend some time on infrastructures for machine learning applications such as Tensorflow. Grading will be based on paper presentations and a final class project requiring parallel programming and performance evaluation on a a parallel computer. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
31665	Lecture-Discussion	PSR	3:30PM -4:45PM	MW	1214 Siebel Center for Comp Sci	Forbes, M	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Pseudorandomness Section Info: Pseudorandomness is the study of efficiently constructing objects that share desirable features of random objects, yet require no randomness to describe. The theory of pseudorandomness influences and draws from areas in computer science such as computational complexity, algorithms, and cryptography; as well as areas of mathematics such as combinatorics and number theory. This course will explore the core aspects of pseudorandomness by constructing foundational pseudorandom objects such as expander graphs, error-correcting codes, randomness extractors and pseudorandom generators, as well as presenting key techniques such as spectral graph theory, (derandomized) concentration bounds, and the polynomial method. Prerequisite: CS 473. 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 OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
68141	Lecture	SG1	12:30PM -1:50PM	TR	3020 Electrical & Computer Eng Bldg	Gupta, S	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Robot Learning Section Info: Same as ECE 598 SG1. Recent developments in learning-based robotics. The course starts with an overview of background from relevant subfields: computer vision, machine learning, robotics and control theory. Next, we 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. The course will conclude with case-studies on robotic navigation, and manipulation from recent papers. 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 OFF - UIUC or MCS:Computer Sci Online -UIUC. Not intended for First Time Freshman students.
39666	Lecture-Discussion	TAL	9:30AM -10:45AM	TR	0218 Siebel Center for Comp Sci	August, T	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Language, Interfaces, and Comm Section Info: In this course, we will explore recent advances in computing for augmenting human communication through language adaptation. We will cover foundational sociolinguistic theories of communication, and investigate new advances in HCI, NLP, and AI that aim to improve how we communicate with one another online. We will learn how to identify when language will impact behavior through empirical studies, and how to design, build and evaluate intelligent reading and writing tools. We will focus class on in-person discussions around research papers and advances. Students will be expected to read papers, post reading reflections, share and comment on papers and ideas, and lead at least one class discussion. The class will culminate in a research project focused on studying language’s effect on behavior and/or building a tool using current language technologies. Classes will not be recorded. 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 OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
46413	Lecture-Discussion	TH1	11:00AM -12:15PM	WF	0218 Siebel Center for Comp Sci	Yuan, W	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Tactile Sensing and Haptics Section Info: Touch is an important perception modality for both humans and robots. This course aims at providing an overview of the touch perception system for both robots and humans, and provide students with some hands-on experience with the popular touch sensors and devices. On the side of robot sensing, the course will cover the topics on the working principles and designs of robot touch sensors, signal processing algorithms for tactile sensing, and the application of tactile sensing in different robotic tasks; on the side of haptics, the course will introduce the neurological and cognitive study in human haptic system, and the designs and applications of haptic devices that provide a human-machine interface. The human-machine interface is a core part of Virtual Reality (VR) and teleoperation of robots when touch is involved. The course includes lectures, research paper presentation and discussion, two lab sessions, and course projects with tactile sensors or haptic devices. Restriction(s): Restricted to Graduate - Urbana-Champaign. Not intended for MCS: Computer Sci OFF - UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
48260	Lecture-Discussion	YP	2:00PM -3:15PM	TR	1310 Digital Computer Laboratory	Park, Y	Part of Term: 1 Date Range: 01/21/25-05/07/25 Credit: 4 hours Section Title: Hot Topics in Data Management Section Info: This "hot topics" course explores emerging trends in data management, including compute-storage disaggregation, VectorDB, Retrieval-Augmented Generation, data science systems, learning-based optimization, privacy-sensitive analytics, stream processing, data lakes, and graph databases. A background in undergraduate-level data management (e.g., CS 411) or equivalent is required. 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.