ECGR 4105: Introduction to Machine Learning
University of North Carolina, Charlotte
Machine learning is a sub-field of Artificial Intelligence that gives computers the ability to learn and/or act without being explicitly programmed. This course examines the necessary theory, principles and algorithms for machine learning.� Topics include: supervised, unsupervised learning approaches (including deep learning), optimization procedures, and statistical inference.� Students digest and practice their knowledge and skills by class discussion, homework, and exams, as well as obtain in-depth experience with a particular topic through a final project.� To prepare students�to be successful in this course, light reviews on linear algebra and matrix analysis and programming tutorials are provided as additional course reading materials.
Average GPA: 3.18
Grade distribution records: 271 students across 9 terms.
Grade distribution
| Grade | Students | Percent |
|---|---|---|
| A | 117 | 43.2% |
| B | 95 | 35.1% |
| C | 31 | 11.4% |
| D | 11 | 4.1% |
| F | 6 | 2.2% |
| W | 11 | 4.1% |
Based on 271 student grade records across 9 terms and 4 professors.
Instructors
- Hamed Tabkhivayghan 168 students, Average GPA 3.17
- Farah Deeba 61 students, Average GPA 3.33
- Vinit Katariya 29 students, Average GPA 3.16
- Andrew Willis 13 students, Average GPA 2.58