|
|
3
|
|
81070
|
Lecture-Discussion
Online
|
FMC
FMC
|
2:00PM
-3:15PM
2:00PM
-3:15PM
|
R
T
|
407 200 S Wacker
n.a.
|
Singh, G
Singh, G
|
- Availability:
- Open (Restricted)
- Part of Term:
- 1
- Date Range:
- 08/24/26-12/09/26
- Section Title:
- FM and ML in Prgm Systems
- Section Info:
- Emerging ML models (like deep neural networks) tend to be complex, fragile, non-robust, and uninterpretable. This makes it extremely challenging to build reliable real-world systems that incorporate ML components. We need trustworthy ML as well as robust system design to achieve end-to-end correctness of systems. In this course, we will study recent developments at the intersection of formal methods (FM), programming languages (PL) and machine learning (ML) research towards the development of trustworthy AI-based systems. Some topics planned covered for the course are: 1. Formal Verification of ML models using abstraction and constraint solvers 2. Symbolic explanations of deep neural networks 3. Training ML models with Logic and Knowledge 4. Learning symbolic concepts (code, program synthesis, invariants) 5. Proving correctness of systems with ML components 6. Neurosymbolic machine learning Recommended prerequisite is CS 440 or CS 477 or a combination of CS 446 and CS 421. Weekly in-person meeting in 200 S. Wacker Dr. There may be in class meetings, exams, and in class activities. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister
- Restriction(s):
-
Restricted to Computer Science or Bioinformatics major(s). Restricted to Graduate - Urbana-Champaign.
Restricted to MCS: Computer Sci OFF - UIUC.
Not intended for First Time Freshman students.
|
|
|
3
|
|
77187
|
Lecture-Discussion
|
FML
|
2:00PM
-3:15PM
|
TR
|
0216 Siebel Center for Comp Sci
|
Singh, G
|
- Availability:
- Open (Restricted)
- Part of Term:
- 1
- Date Range:
- 08/24/26-12/09/26
- Section Title:
- FM and ML in Pgm Systems
- Section Info:
- Emerging ML models (like deep neural networks) tend to be complex, fragile, non-robust, and uninterpretable. This makes it extremely challenging to build reliable real-world systems that incorporate ML components. We need trustworthy ML as well as robust system design to achieve end-to-end correctness of systems. In this course, we will study recent developments at the intersection of formal methods (FM), programming languages (PL) and machine learning (ML) research towards the development of trustworthy AI-based systems. Some topics planned covered for the course are: 1. Formal Verification of ML models using abstraction and constraint solvers 2. Symbolic explanations of deep neural networks 3. Training ML models with Logic and Knowledge 4. Learning symbolic concepts (code, program synthesis, invariants) 5. Proving correctness of systems with ML components 6. Neurosymbolic machine learning Recommended prerequisite is CS 440 or CS 477 or a combination of CS 446 and CS 421. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister
- Restriction(s):
-
Restricted to Computer Science or Bioinformatics major(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.
|
|
|
3
|
|
79800
|
Lecture-Discussion
Online Lecture
|
LCC
LCC
|
12:30PM
-1:45PM
12:30PM
-1:45PM
|
R
T
|
404 200 S Wacker
n.a.
|
Misailovic, S
Misailovic, S
|
- Availability:
- Open (Restricted)
- Part of Term:
- 1
- Date Range:
- 08/24/26-12/09/26
- Section Title:
- ML and Compilers
- Section Info:
- Title: Machine Learning and Compilers. Description: This course covers fundamentals in compilation techniques used in the domain of machine learning. The topics can include tensor programming languages, frameworks, compilers, tensor intermediate representations, code generation for specialized accelerators such as GPUs, dataflow accelerators, tensor program optimizations, automatic differentiation, approximate compilation techniques for neural networks and compilers for probabilistic ML models. Instruction will be lecture based. Grading will be based on projects and quizzes. Weekly in-person meeting in 200 S. Wacker Dr. Restricted to MCS Chicago Students. There may be in class meetings, exams, and in class activities.
- Restriction(s):
-
Restricted to Computer Science or Bioinformatics major(s). Restricted to Graduate - Urbana-Champaign.
Restricted to MCS: Computer Sci OFF - UIUC.
Not intended for First Time Freshman students.
|
|
|
3
|
|
79799
|
Lecture-Discussion
|
LCU
|
12:30PM
-1:45PM
|
TR
|
0220 Siebel Center for Comp Sci
|
Misailovic, S
|
- Availability:
- Open (Restricted)
- Part of Term:
- 1
- Date Range:
- 08/24/26-12/09/26
- Section Title:
- ML and Compilers
- Section Info:
- Title: Machine Learning and Compilers. Description: This course covers fundamentals in compilation techniques used in the domain of machine learning. The topics can include tensor programming languages, frameworks, compilers, tensor intermediate representations, code generation for specialized accelerators such as GPUs, dataflow accelerators, tensor program optimizations, automatic differentiation, approximate compilation techniques for neural networks and compilers for probabilistic ML models. Instruction will be lecture based. Grading will be based on projects and quizzes. Please view the following link for restrictions and release dates: http://go.cs.illinois.edu/csregister.
- Restriction(s):
-
Restricted to Computer Science or Bioinformatics major(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.
|