ML Algorithms
ML Algorithms on AI-ML Companion: Classic ML algorithms - from theory to implementation. 23 interactive modules with live visualizations, quizzes, and hands-on Python coding.
Every module in ML Algorithms is free and open to everyone - no account required.
Modules in this track
- What is Machine Learning? (free) - ML fundamentals and types of learning
- Linear Regression (free) - From scratch implementation
- Logistic Regression (free) - Binary classification
- Regularization (L1/L2/ElasticNet) (free) - Preventing overfitting by penalizing complexity
- Feature Scaling (free) - Normalization and standardization for ML
- Model Evaluation Metrics (free) - Precision, recall, F1, ROC-AUC
- Cross-Validation (free) - K-Fold, stratified splits, reliable evaluation
- Naive Bayes (free) - Probabilistic classifier
- K-Nearest Neighbors (free) - Instance-based learning
- Decision Trees (free) - Tree-based models
- Support Vector Machines (free) - Maximum margin classifiers
- Multiclass Classification (free) - One-vs-All, One-vs-One, softmax strategies
- Neural Networks (free) - Backpropagation from scratch
- K-Means Clustering (free) - Unsupervised learning
- Hierarchical Clustering (free) - Dendrograms and linkage methods
- DBSCAN & Density Clustering (free) - Density-based clustering
- PCA (free) - Dimensionality reduction
- Ensemble Methods (free) - Random forests, bagging
- Gradient Boosting (free) - XGBoost, LightGBM, CatBoost
- Feature Importance & SHAP (free) - Model interpretability and SHAP values
- Handling Imbalanced Data (free) - SMOTE, class weights, resampling strategies
- Project: Algorithm Showdown (free) - Pick the right algorithm for real-world medical diagnosis - compare 6+ models, evaluate with clinical metrics, and explain decisions with SHAP
- Project: IPL Match Predictor (free) - End-to-end ML pipeline on 18 seasons of IPL data - 4-model calibrated ensemble, 20+ features, Monte Carlo validation