CS 521 LCU

Advanced topics in building and verifying software systems, selected from areas of current research such as: model checking and automated verification, testing and automated test generation, program synthesis, runtime verification, machine learning and its applications in the design of verified systems, formal analysis of machine learning algorithms, principles of programming languages and type systems. Course Information: May be repeated if topics vary. Credit is not given towards a degree from multiple offerings of this course if those offerings have significant overlap, as determined by the CS department. Prerequisite: CS 374 or ECE 374; CS 421. Additional prerequisites or corequisites may be specified each term. See section information.

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.