School of Computational Arts & Sciences Undergraduate 6 ECTS
AI310 · Machine Learning Foundations
Covers supervised learning end-to-end: baselines, feature engineering, train/validation discipline, and error analysis. Students practice building reproducible evaluation reports, spotting leakage/overfitting, and communicating results with clear metrics and caveats.
- ml
- evaluation
- fundamentals
| Overview | Details | Notes |
|---|---|---|
| Code | AI310 | — |
| Title | Machine Learning Foundations | — |
| School | School of Computational Arts & Sciences | — |
| Level | Undergraduate | — |
| Credits | 6 ECTS | — |
What you will learn
- · Build supervised learning baselines and compare them fairly
- · Run error analysis to diagnose leakage and overfitting
- · Communicate results with clear metrics and caveats
Prerequisites
No formal prerequisites (or equivalents are accepted).
Assessment
| Component | Weight |
|---|---|
| Assignments | 60% |
| Evaluation report | 40% |
Weekly outline
Week 1: Setup + evaluation discipline
3 topics
- · Train/validation splits
- · Baselines
- · Reproducible experiments
Week 2: Features + models
3 topics
- · Feature engineering
- · Model selection
- · Regularization
Week 3: Error analysis
3 topics
- · Slicing
- · Leakage checks
- · Overfitting diagnosis
Week 4: Reporting
3 topics
- · Metrics
- · Caveats
- · Recommendations