CS 598

Spring 2024 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 2024
CRN	Type	Section	Time	Day	Location	Instructor	Section Details
48247	Lecture-Discussion	AIE	2:00PM -3:15PM	TR	1214 Siebel Center for Comp Sci	Zhang, M	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: AI Efficiency: Sys. & Algor. Section Info: Are you curious about how system techniques enable today's large-scale model training and deliver ultra-fast inference? Do you have a passion for making AI accessible to all by using advanced system and algorithm techniques, thereby significantly reducing the cost of training and deploying deep learning models? If so, this course is for you. The course provides an in-depth view of AI efficiency, focusing on the core concepts of both AI systems and algorithmic methods. We will explore and discuss seminal works in the field of AI systems, such as ZeRO-style data parallelism, tensor parallelism, pipeline parallelism, sequence parallelism, and 3D parallelism. We will also go over inference optimization techniques, such as FlashAttention, blocked KV cache, speculative decoding, and various compression algorithms. Students will have the opportunity to present existing works in the field of AI efficiency and learn to write paper reviews, which help develop critical thinking skills. Students will also work on group projects, which involve the design, hands-on implementation, and evaluation of AI systems or algorithms. The group project will provide students with valuable experience in working with real AI systems, and a deeper understanding of the complexities involved in optimizing AI efficiency. 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.
69012	Lecture-Discussion	APK	11:00AM -12:15PM	TR	1302 Siebel Center for Comp Sci	Kloeckner, A	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Fast Algor & Integral Equat.'s Section Info: Near-linear-complexity ("fast") numerical algorithms and related numerical methods, mainly for the numerical solution of elliptic partial differential equations, such as Laplace, Helmholtz, Stokes, Maxwell's, or elasticity. Numerical rank, complexity/accuracy trade-offs, notions of convergence. Multi-level compression schemes. Tree codes, Fast Multipole Methods. Potential Theory and Integral Equations. Quadrature. Fast, compression-based, linear-time direct solvers based, randomized linear algebra. Fast function transforms: Uniform and non-uniform FFTs, Butterfly algorithms. Prerequisites: Linear Algebra, programming experience, some exposure to Partial Differential Equations. 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.
39665	Lecture-Discussion	DH	11:00AM -12:15PM	TR	1214 Siebel Center for Comp Sci	Heath, D	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Secure Computation Section Info: This course covers secure multiparty computation (MPC), a suprisingly powerful branch of cryptography that allows mutually untrusting parties to work together to securely run programs on private data. We will discuss both the theory and the practice of this emerging technology. Our discussion will cover computing on encrypted data, zero-knowledge proofs, oblivious RAM, and more. Suggested Prerequisites: CS 374, CS 361. Mathematical maturity is required; participants will be expected to read and write formal definitions/proofs, and to read and present research papers. Basic background on probability theory is recommended. Formal cryptography background is explicitly 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 Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC. Not intended for First Time Freshman students.
43771	Lecture-Discussion	DHT	2:00PM -3:15PM	WF	3217 Everitt Laboratory	Hakkani Tur, D	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Conversational AI Section Info: The goal of this course is to cover advanced research topics about conversational AI systems and review founding papers as well as recent work in task-oriented dialog systems, open-domain and social conversational systems, and conversations with embodied systems. We will review previous work on component-wise approaches, as well as end-to-end systems based on large language models (such as ChatGPT), and discuss where they converge and diverge. The target audience is graduate students who plan to or are already working on these topics. As our time permits, I also plan to invite leading researchers in this field to present guest lectures. Students are expected to propose and work on a research project in one of these areas; we will discuss the proposals and progress throughout the course. In addition to preparing their final projects, students will present paper reviews, and will do a peer review of others' proposals and project reports. 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.
43732	Online	DLH	ARRANGED	n.a.	n.a.	Sun, J	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Deep Lrng for Healthcare Section Info: This course covers deep learning (DL) methods, healthcare data, and applications using DL methods. For this semester, we will emphasize deep learning for drug discovery and development use cases. The students will be expected to review book chapters and answer homework assignments related to ML for drug discovery and development and other healthcare applications. The courses include activities such as video lectures, self-guided programming labs, homework assignments (both written and programming), and a large project. You are expected to learn deep learning models such as deep neural networks, convolutional neural networks, recurrent neural networks, autoencoder, attention models, graph neural networks and deep generative learning. You will also get a chance to learn 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. Besides learning DL algorithms, the course will focus on hands-on experiences for data scientists and machine learning engineers to implement various practical healthcare models on diverse medical data. You will learn popular deep learning frameworks like PyTorch, and data science software like Jupyter Notebook. Basic machine learning will be helpful but not strictly required. You should have good programming skills in Python and good understanding in linear algebra and calculus. You should also have sufficient system knowledge such as using Linux and setting up programming environments on the cloud. This course is only for students that are in the Computer Science MCS-DS Program. Additional ProctorU fees may apply. 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. Restricted to MCS:Computer Sci Online -UIUC.
65866	Online	DSO	ARRANGED	n.a.	n.a.	Park, T	Part of Term: 1 Date Range: 01/16/24-05/01/24 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 MCS:Computer Sci Online -UIUC, MCS:Computer Sci Online -UIUC, or NDEG:Computer Science Onl-UIUC.
31662	Lecture-Discussion	EKS	2:00PM -3:15PM	TR	1304 Siebel Center for Comp Sci	Soltanaghai, E	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Smart cities, homes, & beyond Section Info: This course explores the principles and practice of smart physical places and things (Smart). New devices have been added to cities, homes, factories, cars, and even to humans (inside and out), hoping that this influx of technology will help us solve pressing societal issues in all facets of life such as energy, personal health, environment, or safety. The challenges, however, remain in designing and scaling the hardware platforms, networking protocols, and machine perception algorithms to enable this new class of computing. This course will cover state-of-the-art research papers that address various visions of the future platforms supporting smart. It will also stress the cyber physical aspects of these systems, providing safe, secure, and efficient interaction with the physical world. This course will offer significant hands-on experience through a semester-long project, paper critiques, and overview of the commercial landscapes for the topics covered in class. https://elahe.web.illinois.edu/598EKS.html) 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.
54551	Lecture-Discussion	GC	11:00AM -12:15PM	WF	3217 Everitt Laboratory	Chowdhary, G	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Robotics Section Info: 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.
39670	Lecture-Discussion	JHR	11:00AM -12:15PM	WF	2200 Sidney Lu Mech Engr Bldg	Hockenmaier, J	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Embodied Natural Language Proc Section Info: In this class, we will discuss both classical and current research on natural language understanding and generation for embodied AI (both virtual agents and robots) What are the main challenges in getting systems to follow (or give) instructions or engage in a dialogue with human users in real or simulated 3D spaces, including games such as Minecraft? What tasks, scenarios, and platforms are suitable for research in this domain? How far can LLMs get us? Where do we have go to beyond them? 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.
43782	Lecture-Discussion	KCC	3:00PM -4:15PM	TR	0218 Siebel Center for Comp Sci	Chang, K	Part of Term: 1 Date Range: 01/16/24-05/01/24 Special Approval: Instructor Approval Required 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 are 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 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 research papers. Format: hands-on search in small groups of 1-2 leads and 1-2 apprentices. Prerequisites: 1) Leads- Research experience in NLP/ML/DM (having published in ACL/EMNLP or similar venues) and 2) Apprentices: CS447 and strong CS background. Instructor consent 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.
62819	Online	LHO	ARRANGED	n.a.	n.a.	Sun, J	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Deep Learning For Healthcare Section Info: This course covers deep learning (DL) methods, healthcare data, and applications using DL methods. For this semester, we will emphasize deep learning for drug discovery and development use cases. The students will be expected to review book chapters and answer homework assignments related to ML for drug discovery and development and other healthcare applications. The courses include activities such as video lectures, self-guided programming labs, homework assignments (both written and programming), and a large project. You are expected to learn deep learning models such as deep neural networks, convolutional neural networks, recurrent neural networks, autoencoder, attention models, graph neural networks and deep generative learning. You will also get a chance to learn 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. Besides learning DL algorithms, the course will focus on hands-on experiences for data scientists and machine learning engineers to implement various practical healthcare models on diverse medical data. You will learn popular deep learning frameworks like PyTorch, and data science software like Jupyter Notebook. Basic machine learning will be helpful but not strictly required. You should have good programming skills in Python and good understanding in linear algebra and calculus. You should also have sufficient system knowledge such as using Linux and setting up programming environments on the cloud. Section LHO is not intended for online MCS students. This is the on-campus section. Additional ProctorU fees may apply. Restriction(s): Restricted to Computer Science or Bioinformatics major(s).
40659	Lecture-Discussion	LMZ	9:30AM -10:45AM	TR	3025 Campus Instructional Facility	Zhang, L	Part of Term: 1 Date Range: 01/16/24-05/01/24 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.
69011	Lecture-Discussion	MEB	2:00PM -3:15PM	TR	1302 Siebel Center for Comp Sci	El-Kebir, M	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Computational Cancer Genomics Section Info: Title: Computational cancer genomics This course focuses on recent algorithmic methods in cancer genomics, including somatic variant calling, phylogeny inference and identification of driver mutations. Students will study the underlying principles of these methods and the application of these methods to cancer genomics data. This course is appropriate for graduate students in computer science, bioengineering, mathematics and statistics. Familiarity with basic statistics, probability and algorithms is expected. 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.
43806	Lecture-Discussion	QC	2:00PM -3:15PM	MW	1302 Siebel Center for Comp Sci	Sinha, M	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Frontiers of Quantum Complex. Section Info: This is an advanced, PhD-level topics class in quantum complexity theory — the study of the fundamental capabilities and limitations of quantum computers. One of the central themes of the course will be to understand quantum advantage — what can be done with quantum resources that is not possible otherwise — and its ties to cryptography and physics. The course will start with the fundamentals of quantum information and quantum complexity covering: - The complexity class BQP and how it relates to classical complexity classes such as P, BPP - Quantum query complexity - The power of quantum witnesses and proofs - The Local Hamiltonian Problem Following this we will explore some topics of current research interest. A list of possible topics include: - Near-term quantum advantage such as random circuit and Boson sampling - Complexity of quantum states and transformations - Quantum Pseudorandomness - Connections to Black holes and Quantum gravity - Questions related to condensed matter physics, such as Area Laws, NLTS and the Quantum PCP Conjecture The goal is to explore the results and (more importantly) the questions in this field in order to bring the students to the research frontier. Key prerequisite for this course is mathematical maturity. While no quantum mechanics background is needed, some familiarity with classical complexity classes (P, NP) and basic quantum computing is beneficial. Course work may include: scribe notes, a few assignments, and a course project. 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.
65119	Lecture-Discussion	TZ	2:00PM -3:15PM	TR	1035 Campus Instructional Facility	Zhang, T	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Principles of Generative AI Section Info: Recent advancements in generative AI have equipped machine learning algorithms with the ability to learn from and accurately replicate observed data, creating new, similar data instances. This course provides an in-depth exploration of the key algorithmic developments in generative models, together with their underlying mathematical principles. We will cover a range of topics such as normalizing flows, variational autoencoders, Langevin algorithms, generative adversarial networks, diffusion models, and sequence generation models, etc. 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.
58019	Lecture-Discussion	YL	3:30PM -4:45PM	TR	1035 Campus Instructional Facility	Li, Y	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: Deep Lrng. for Robotic Manip. Section Info: This course offers an in-depth examination of the integration of deep learning techniques with robotic manipulation. In the real-world environment, successful robotic manipulation requires careful consideration of system-level designs spanning perception, dynamics, and decision-making modules. This course will investigate various robotic manipulation tasks across different horizons, encountering objects made of diverse materials – from rigid to deformable, granular to cloth. We will provide an in-depth analysis of how state-of-the-art deep learning applications can equip robots with novel manipulation capabilities and discuss their advantages over classic approaches. The course will include paper reviews, hands-on projects, and insights into the principles behind state-of-the-art solutions. 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.
48260	Lecture-Discussion	YP	2:00PM -3:15PM	TR	1310 Digital Computer Laboratory	Park, Y	Part of Term: 1 Date Range: 01/16/24-05/01/24 Credit: 4 hours Section Title: ML and Data Systems Section Info: This course will explore the intersection between machine learning (ML) and data systems. After introducing the modern system architecture that embarked on the "big data" era, we will observe the influence of AI and ML techniques on data system research by studying the latest research papers in the areas of systems for large-scale analytics/data science/machine learning, and ML for unstructured data management. An important part of this course will be a final project, which will either be: 1) a novel research contribution, 2) reproducing existing work, with thorough documentation, or 3) a synthesis of the literature in a final report and blog post. Prerequisites: CS 411 (databases) and CS 440 (AI). Or equivalent experience for both. 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.