Foundations

Linear algebra (matrices → eigen → SVD), calculus (derivatives → chain rule → Jacobians), then features, probability, and information theory — the math building blocks of ML.

• Vector Math
• Matrix Multiply
• Inverse Matrix
• Eigenvalues & Eigenvectors
• SVD & Orthogonality
• Derivatives
• Chain Rule
• Jacobians
• Gradient Geometry
• Feature Scaling
• Distance Metrics
• Covariance & Correlation
• Dot Product & Angles
• Softmax & Probabilities
• Train/Val & Bias–Variance
• Probability & Bayes
• Gaussian Distribution
• Hypothesis Testing
• Entropy & Cross-Entropy
• Information Gain

KousKrab — interactive ML simulations in the browser.