2AI4203: Machine Learning
Fall 2026, Korea Aeropace University
Fall 2026, Korea Aeropace University
Course Logistics
Instructor
Teaching Assistants
Lecture
Office Hours
Grading
Jiyoon Shin (jiyoonshin@kau.ac.kr)
Minjae Won (lgtwins2003@gmail.com), Jinju Kim (pmsuk4023@naver.com)
Wednesday, 14:00-18:00
Electronics Building, Room 422
Tuesday/Thursday, 14:00-17:00
Electronics Building, Room 403
Midterm Exam: 30%
Final Exam: 30%
Homework Assignments: 30%
Attendance: 10%
Homework Assignments
Homework assignments should be submitted via LXP.
Late submissions will not be accepted.
Assignment Number
1
2
3
4
Date/Time Assigned
Sep. 24 at 12:00am
Oct. 15 at 12:00am
Nov. 12 at 12:00am
Dec. 03 at 12:00am
Date/Time Due
Sep. 30 at 23:59pm
Oct. 19 at 11:59am
Nov. 18 at 23:59pm
Dec. 07 at 11:59am
Document Link
Lecture Slides
Date
Sep.02
Sep.09
Sep.16
Sep.23
Sep.30
Oct. 07
Oct. 14
Oct. 21
Oct. 28
Nov.04
Nov. 11
Nov.18
Nov.25
Dec.02
Dec.09
Topic
Part I: Foundations of Machine Learning
Lecture 1: Introduction to Machine Learning
Lecture 2: Machine Learning Basics & Linear Regression
Lecture 3: Classification with Machine Learning
Lecture 4: Model Evaluation & Generalization
Lecture 5: Tree-Based Machine Learning Models
Lecture 6: Advanced Classification & Ensemble Methods
Lecture 7: Unsupervised Learning
Midterm Exam
Part II: Modern Machine Learning: Practice & Reliability
Lecture 8: Machine Learning in Practice
Lecture 9: Neural Networks & Representation Learning
Lecture 10: Trustworthy & Explainable Machine Learning
Lecture 11: Machine Learning under Distribution Shift
Lecture 12: Data-Centric Machine Learning
Lecture 13: Foundation Models & Emerging ML Paradigms
Final Exam
Description
- Course Overview
- What is Machine Learning?
- AI vs. ML vs. DL
- Applications of Machine Learning
- Supervised vs. Unsupervised Learning
- Classification vs. Regression
- Machine Learning Workflow
- Linear Regression
- Loss Functions
- Gradient Descent
- Logistic Regression
- Probabilistic Classification
- Decision Boundaries
- Classification Loss Functions
- Binary vs. Multiclass Classification
- Train/Validation/Test Split
- Cross-Validation
- Performance Metrics
- Overfitting & Underfitting
- Bais-Variance Tradeoff
- Regularization
- Generalization
- Decision Trees
- Splitting Criteria
- Bagging
- Random Forests
- Feature Importance
- Support Vector Machines
- Kernel Methods
- Ensemble Learning
- Gradient Boosting
- XGBoost / LightGBM
- Principal Component Analysis (PCA)
- K-Means Clustering
- Hierarchical Clustering
- Dimensionality Reduction
- Clustering Evaluation & Visualization
- Data Preprocessing
- Feature Engineering
- Data Leakage
- Model Selection
- Hyperparameter Optimization
- Machine Learning Pipelines
- Common Pitfalls
- From Linear Models to Neural Networks
- Multi-Layer Perceptrons (MLPs)
- Activation Functions
- Forward & Backpropagation
- Gradient-Based Learning
- Representation Learning
- From Neural Networks to Deep Learning
- Model Interpretability & Explainability
- Feature Importance & SHAP
- Prediction Confidence & Calibration
- Uncertainty Estimation
- Fairness & Bias
- Adversarial Robustness
- Introduction to Conformal Prediction
- Distribution Shift
- Covariate / Label / Concept Shift
- Out-of-Distribution (OOD) Detection
- Domain Adaptation
- Domain Generalization
- Robust Learning under Distribution Shift
- Data Quality
- Label Noise
- Class Imbalance & Long-Tailed Data
- Dataset Bias
- Sampling Strategies
- Data Augmentation
- Data-Centric AI
- Task-Specific Models to Foundation Models
- Attention & Transformers
- Pretraining & In-Context Learning
- Foundation Models beyond Language
- Tabular Foundation Models & TabPFN
- AutoML & Automated ML Pipelines
- Future Directions in Machine Learning