2AI4203 Machine Learning

Fall 2026 · Korea Aerospace University

Course Information

Instructor	Jiyoon Shin · jiyoonshin@kau.ac.kr
Teaching Assistants	Minjae Won · lgtwins2003@gmail.com Yewon Hwang · hamcheese8989@kau.kr
Lecture	Wednesday 14:00–18:00 · Electronics Building 422
Office Hours	Tuesday / Thursday 14:00–17:00 · Electronics Building 403
Grading	Midterm 30% · Final 30% · Homework 30% · Attendance 10%

Homework Assignments

Homework assignments should be submitted via LXP.
Late submissions will not be accepted.

Assignment	Assigned	Due	Document
Homework 1	Sep. 24 at 00:00	Sep. 30 at 23:59	Assignment PDF
Homework 2	Oct. 15 at 00:00	Oct. 18 at 23:59	Assignment PDF
Homework 3	Nov. 12 at 00:00	Nov. 18 at 23:59	Not yet posted
Homework 4	Dec. 03 at 00:00	Dec. 06 at 23:59	Not yet posted

Lecture Slides

Course schedule and downloadable materials

Date	Topic	Description	Documents
Part I: Foundations of Machine Learning
Sep. 02	Lecture 1 Introduction to Machine Learning	Course overview What is machine learning? AI vs. ML vs. DL Applications of machine learning	Slides PDF
Sep. 09	Lecture 2 Learning from Data & Linear Regression	Data & learning paradigms Classification vs. regression Machine learning workflow Linear regression Loss functions Gradient descent	Slides PDF With notes PDF
Sep. 16	Lecture 3 Classification with Linear Models	Binary classification Logistic regression Sigmoid & binary cross-entropy Multiclass classification Softmax & cross-entropy	Slides PDF With notes PDF
Sep. 23	Lecture 4 Model Evaluation and Generalization	Data splits & model selection Cross-validation Performance metrics Underfitting & overfitting Bias-variance tradeoff Regularization & early stopping	Slides PDF With notes PDF
Sep. 30	Lecture 5 Tree-Based Machine Learning Models	Decision trees Splitting criteria Tree complexity & pruning Bagging & random forests OOB evaluation & feature importance	Slides PDF With notes PDF
Oct. 07	Lecture 6 Support Vector Machines & Boosting	Feature scaling Support vector machines Kernel methods & nonlinear SVM Bagging vs. boosting AdaBoost & gradient boosting XGBoost & LightGBM	Slides PDF With notes PDF
Oct. 14	Lecture 7 Dimensionality Reduction & Clustering	Unsupervised learning Principal component analysis K-means clustering Hierarchical clustering Clustering evaluation	Slides PDF With notes PDF
Oct. 21	Midterm Exam	—	—
Part II: Modern Machine Learning: Practice & Reliability
Oct. 28	Lecture 8 Machine Learning in Practice	Data preprocessing Feature engineering Data leakage Model selection Hyperparameter optimization Machine learning pipelines Common pitfalls	Slides PDF With notes PDF
Nov. 04	Lecture 9 Neural Networks & Representation Learning	From linear models to neural networks Multi-layer perceptrons Activation functions Forward & backpropagation Gradient-based learning Representation learning	Not yet posted
Nov. 11	Lecture 10 Trustworthy & Explainable Machine Learning	Interpretability & explainability Feature importance & SHAP Confidence & calibration Uncertainty estimation Fairness, bias & adversarial robustness Conformal prediction	Not yet posted
Nov. 18	Lecture 11 Machine Learning under Distribution Shift	Distribution shift Covariate, label & concept shift OOD detection Domain adaptation & generalization Robust learning	Not yet posted
Nov. 25	Lecture 12 Data-Centric Machine Learning	Data quality Label noise Class imbalance & long-tailed data Dataset bias Sampling & augmentation Data-centric AI	Not yet posted
Dec. 02	Lecture 13 Foundation Models & Emerging ML Paradigms	Foundation models Attention & transformers Pretraining & in-context learning Foundation models beyond language TabPFN & AutoML Future directions	Not yet posted
Dec. 09	Final Exam	—	—