Teori:

1. Pengantar Machine Learning: Definisi ML, sejarah, taksonomi (supervised, unsupervised, reinforcement), workflow ML pipeline, hubungan dengan AI dan Deep Learning, aplikasi industri
2. Data Preprocessing & Feature Engineering: Tipe data, handling missing values, outlier detection, normalisasi/standardisasi, encoding kategorikal, feature selection dan extraction
3. Supervised Learning: Regresi: Linear regression, polynomial regression, regularisasi (Ridge, Lasso, Elastic Net), asumsi regresi, interpretasi koefisien
4. Supervised Learning: Klasifikasi I: Logistic regression, K-Nearest Neighbors, decision boundary, probabilistic interpretation, multi-class classification
5. Supervised Learning: Klasifikasi II: Decision Tree, Random Forest, ensemble methods (bagging), feature importance, pruning, hyperparameter tuning
6. Support Vector Machine & Kernel Methods: SVM linear dan non-linear, kernel trick (RBF, polynomial), soft margin, SVM untuk klasifikasi dan regresi
7. Evaluasi Model & Validasi: Metrics (accuracy, precision, recall, F1, ROC-AUC, RMSE, MAE), cross-validation, bias-variance tradeoff, learning curves, overfitting vs underfitting
8. UTS
9. Unsupervised Learning: Clustering: K-Means, hierarchical clustering, DBSCAN, silhouette score, elbow method, aplikasi segmentasi
10. Unsupervised Learning: Dimensionality Reduction: Principal Component Analysis (PCA), t-SNE, explained variance, aplikasi untuk visualisasi dan feature reduction
11. Ensemble Methods & Model Selection: Gradient Boosting, XGBoost, LightGBM, stacking, model comparison strategy, AutoML introduction
12. Naive Bayes & Probabilistic Models: Bayes theorem, Gaussian/Multinomial/Bernoulli Naive Bayes, conditional independence assumption, text classification foundation
13. Introduction to Neural Networks for ML: Perceptron, Multi-Layer Perceptron (MLP), backpropagation basics, activation functions, sebagai jembatan ke Deep Learning
14. ML Deployment & MLOps Basics: Model serialization (pickle, joblib), REST API basics, containerization concept, monitoring, ethical considerations in ML
15. Presentasi Proyek Praktik Lapang
16. UAS

Praktikum:

1. Setup environment: Python, Jupyter, Scikit-learn, Pandas, NumPy. Eksplorasi dataset sederhana (Iris, MNIST preview)
2. Implementasi preprocessing pipeline menggunakan Pandas dan Scikit-learn pada dataset real (housing/customer data)
3. Implementasi model regresi untuk prediksi harga/nilai kontinyu, visualisasi dengan Matplotlib/Seaborn
4. Klasifikasi dataset (customer churn, spam detection), confusion matrix visualization
5. Implementasi tree-based models, visualisasi decision tree, feature importance analysis
6. SVM implementation pada dataset high-dimensional, kernel comparison experiments
7. Comprehensive model evaluation, cross-validation implementation, hyperparameter tuning dengan GridSearchCV
8. Ujian praktikum: implementasi pipeline ML lengkap
9. Customer segmentation project, clustering visualization, cluster profiling
10. Reduksi dimensi dataset high-dimensional, visualisasi hasil PCA dan t-SNE
11. Implementasi boosting algorithms, model comparison pipeline, feature engineering lanjutan
12. Text classification (sentiment analysis, document categorization) menggunakan Naive Bayes
13. MLP implementation dengan Scikit-learn dan Keras/TensorFlow dasar untuk klasifikasi
14. Model deployment menggunakan Flask/FastAPI, simple web interface untuk prediksi
15. Ujian praktikum: end-to-end ML project

Praktik Lapang:

1. Observasi awal: identifikasi potensi penerapan ML di organisasi mitra
2. Pengumpulan data dari organisasi mitra untuk proyek
3. Analisis kebutuhan dan preprocessing data organisasi mitra
4. Progress report proyek praktik lapang
5. Implementasi model pada data organisasi mitra
6. Presentasi hasil implementasi ML di organisasi mitra: problem definition, metodologi, hasil, dan rekomendasi
7. Pengumpulan laporan akhir praktik lapang