Overall numerical course grades will be determined as the weighted average of the following three categories. Note that there is no final exam, only the final project.
| Category | Grade Weight | Note |
| Homework Assignments | 25% | 8 total, weighted equally |
| Exam 1 | 25% | Better of Exam 1 and Exam 1 Retake, if completing the optional Retake |
| Exam 2 | 25% | Better of Exam 2 and Exam 2 Retake, if completing the optional Retake |
| Final Project | 25% | No final exam, just project |
Course letter grades will be assigned based on numerical course grades according to the following threshold function. There is no curve, meaning your grade does not depend on the grades of your peers. There is no rounding; a numerical course grade must be strictly greater than or equal to the given threshold to earn the given letter.
| Letter Grade | Threshold | Letter Grade | Threshold |
| A+ | 97 | C+ | 77 |
| A | 93 | C | 73 |
| A- | 90 | C- | 70 |
| B+ | 87 | D+ | 67 |
| B | 83 | D | 63 |
| B- | 80 | D- | 60 |
Homework will be graded for completeness, correctness, and clarity at the task level. The cover sheets of individual homework assignments will specify the number of points for that homework assignment broken down by part and task. Tests will be graded for correctness.
The final project will be evaluated for (i) completing the submission requirements and specifications, (ii) incorporating relevant methodologies, and (iii) demonstrating meaningful applications in machine learning. A separate and detailed item-level rubric will be provided for the final project as a handout at midterm after the first exam.
