Machine Learning
Core ML concepts, learning paradigms, algorithms, evaluation, and deployment
ML FundamentalsTraining, inference, features, labels, loss functions, optimization›Supervised LearningRegression, classification; linear models, SVMs, decision trees, ensembles›Unsupervised LearningClustering (k-means, DBSCAN), dimensionality reduction (PCA, t-SNE)›Reinforcement LearningReward signals, policy, Q-learning, actor-critic, games and robotics›Neural Networks & Deep LearningPerceptrons, backpropagation, CNNs, RNNs, transformers, attention mechanism›Model EvaluationAccuracy, precision, recall, F1, AUC-ROC, confusion matrix, cross-validation›Feature EngineeringNormalization, encoding, selection, extraction, handling missing data›ML Pipeline & MLOpsData prep, training, evaluation, deployment, monitoring, model registry›ML Algorithm CheatsheetHow to choose the right algorithm — decision guide by problem type, data size, and accuracy needs›