Machine Learning Basics

Supervised regression mathematics, logistic classification, evaluation metrics, K-Means clustering, PCA dimensionality reduction, and neural backpropagation.

1Supervised Learning & Regression Mathematics

Ordinary Least Squares closed-form derivation, Normal Equation matrix algebra, Mean Squared Error loss surfaces, and Gradient Descent optimization.

Supervised Learning & Regression Mathematics

Master linear regression, derive the Normal Equation, and implement analytical Ordinary Least Squares estimators from first principles.

Supervised Learning & Regression Mathematics

Explore supervised regression mathematics, derive the analytical Ordinary Least Squares Normal Equation, analyze loss convexity, and compare Gradient Descent variants.

2Classification Algorithms & Model Evaluation

Logistic regression, Sigmoid activation, Binary Cross-Entropy loss, Confusion Matrix mechanics, Precision, Recall, and F1-Score.

Classification Algorithms & Model Evaluation

Implement probabilistic logistic classification and evaluate models using Precision, Recall, and F1-Score on imbalanced datasets.

Classification Algorithms & Model Evaluation

Master binary classification algorithms, unpack the mathematical properties of the Sigmoid function, derive Binary Cross-Entropy loss, and calculate confusion matrix metrics.

3Unsupervised Learning: Clustering & Dimensionality

K-Means Lloyd relaxation, inertia minimization, Curse of Dimensionality, sample covariance matrices, and Principal Component Analysis (PCA).

Unsupervised Learning - Clustering & Dimensionality

Discover latent geometric structures in unlabeled data using K-Means clustering and reduce feature dimensionality via PCA.

Unsupervised Learning - Clustering & Dimensionality

Analyze unsupervised clustering mechanics with K-Means, prove convergence properties under Lloyd's relaxation, and reduce feature dimensionality using PCA eigenvalue decomposition.

4Neural Network Fundamentals & Backpropagation

Multi-Layer Perceptrons, Universal Approximation Theorem, non-linear activations (ReLU), computational graphs, and reverse-mode automatic differentiation.

Neural Network Fundamentals & Backpropagation

Construct neural network computational graphs from scratch and derive analytical backpropagation using the multivariable chain rule.

Neural Network Fundamentals & Backpropagation

Build multi-layer perceptrons from scratch, analyze non-linear activations like ReLU, derive the multivariable chain rule for backpropagation, and compute weight gradients.