CS 224: FOUNDATIONS OF MACHINE LEARNING
University of California, Riverside
4 Units, Lecture, 3 hours; research, 3 hours. Prerequisite(s): CS 100; STAT 155 or EE 114; MATH 031; For the CS 224/EE 242A online section: enrollment in the Online Master-in-Science in Engineering program; graduate standing.; graduate standing; or consent of instructor. A study of generative and discriminative approaches to machine learning. Topics include probabilistic model fitting, gradient-based loss optimization, regularization, hyper-parameters, and generalization. Includes experience with data science programming environments, data from practice, and performance metrics. May be taken Satisfactory (S) or No Credit (NC) with consent of instructor and graduate advisor. Cross-listed with EE 242A.
Average GPA: 3.47
Grade distribution records: 324 students across 5 terms.
Grade distribution
| Grade | Students | Percent |
|---|---|---|
| A+ | 38 | 11.7% |
| A | 123 | 38.0% |
| A- | 39 | 12.0% |
| B+ | 25 | 7.7% |
| B | 45 | 13.9% |
| B- | 18 | 5.6% |
| C+ | 10 | 3.1% |
| C | 10 | 3.1% |
| C- | 6 | 1.9% |
| F | 5 | 1.5% |
| NP | 2 | 0.6% |
| S | 3 | 0.9% |
Based on 324 student grade records across 5 terms and 3 professors.
Instructors
- Amit Roy Chowdhury 133 students, Average GPA 3.28
- Gregory Ver Steeg 110 students, Average GPA 3.89
- Christian Shelton 81 students, Average GPA 3.21