Olox Olox

Theme

Documentation
Back to Home

Mathematics for AI

Linear algebra, calculus, probability, and statistics

Linear algebra, calculus, probability, and statistics

Sections

Articles

Calculus for Deep Learning: Derivatives, Gradients, and Chain Rule Explained

Master the calculus foundations for deep learning. Learn derivatives, gradients, partial …

15 min

Probability Distributions for Machine Learning: Complete Guide

Master probability distributions essential for ML. Learn Gaussian, Bernoulli, Poisson, and more with …

15 min

Backpropagation Explained: How Neural Networks Actually Learn

Master backpropagation with step-by-step derivations, computational graphs, and practical code …

15 min

Bayes' Theorem Explained: From Basics to Bayesian Machine Learning

Master Bayes' theorem for machine learning. Learn prior, posterior, likelihood with intuitive …

15 min

Gradient Descent Optimizers: SGD, Adam, RMSprop Complete Comparison

Master gradient descent optimizers with practical examples. Compare SGD, Momentum, Adam, RMSprop, …

15 min

MLE vs MAP: Maximum Likelihood and Bayesian Parameter Estimation

Master MLE and MAP estimation for machine learning. Learn when to use each, mathematical …

13 min

Learning Rate Schedules: Warmup, Cosine Annealing, and One-Cycle Policy

Master learning rate scheduling for deep learning. Implement warmup, step decay, cosine annealing, …

13 min

Statistical Inference for ML: Hypothesis Testing and Confidence Intervals

Master statistical inference for machine learning. Learn hypothesis testing, p-values, confidence …

15 min

Convex Optimization for Machine Learning: From Lagrange to KKT Conditions

Master convex optimization fundamentals for machine learning. Learn convex functions, Lagrange …

14 min

Covariance, Correlation, and Multivariate Distributions in ML

Master covariance matrices, correlation analysis, and multivariate distributions for machine …

13 min

Information Theory: Entropy, Cross-Entropy, and KL Divergence

Master information theory for machine learning. Learn entropy, cross-entropy loss, KL divergence, …

16 min

Second-Order Optimization Methods: Newton, Quasi-Newton, and L-BFGS for Machine Learning

Master second-order optimization methods for machine learning. Learn Newton's method, Quasi-Newton, …

14 min