CSE 40: ML Basics
University of California, Santa Cruz
Introduction to the basic mathematical concepts and programming abstractions required for modern machine learning, data science, and empirical science. The mathematical foundations include basic probability, linear algebra, and optimization. The programming abstractions include data manipulation and visualization. The principles of empirical analysis, evaluation, critique and reproducibility are emphasized. Mathematical and programming abstractions are grounded in empirical studies including data-driven evidential reasoning, predictive modeling, and causal analysis.
Average GPA: 3.35
Grade distribution records: 1,681 students across 11 terms.
Grade distribution
| Grade | Students | Percent |
|---|---|---|
| A+ | 77 | 4.6% |
| A | 497 | 29.6% |
| A- | 263 | 15.6% |
| B+ | 143 | 8.5% |
| B | 257 | 15.3% |
| B- | 106 | 6.3% |
| C+ | 59 | 3.5% |
| C | 63 | 3.7% |
| C- | 7 | 0.4% |
| D+ | 5 | 0.3% |
| D | 10 | 0.6% |
| D- | 4 | 0.2% |
| F | 27 | 1.6% |
| P | 106 | 6.3% |
| NP | 38 | 2.3% |
| W | 18 | 1.1% |
Based on 1,681 student grade records across 11 terms and 5 professors.
Instructors
- Lise Getoor 868 students, Average GPA 3.30
- Alexander J Rudnick 340 students, Average GPA 3.27
- Hao Yue 177 students, Average GPA 3.61
- Niloofar Montazeri 169 students, Average GPA 3.41
- Yang Liu 127 students, Average GPA 3.47