All Articles ever
Information Theory: The Convergence of Machine Intelligence
The grand finale. Discover how Entropy, KL Divergence, and the Principle of Maximum Entropy unify all mathematical pillars into a single framework for measuring and mastering information.
Advanced Multivariable Calculus: The Geometry of Deep Learning
Master the advanced geometry of loss landscapes. Explore the Jacobian and Hessian matrices, Taylor expansions, and the complex calculus that powers backpropagation in modern deep learning.
Statistics for ML: Evaluation and Inference
Move beyond simple accuracy. Explore the statistical foundations of model evaluation: from hypothesis testing and confidence intervals to the fundamental bias‑variance tradeoff.
Optimization for ML: Beyond Gradient Descent
This article explores the optimization landscape: from convex to non‑convex problems, from first‑order to second‑order methods, and from simple SGD to adaptive algorithms like Adam and RMSprop.
Probability for ML From Bayes' Theorem to Generative Models
Probability theory is the mathematics of uncertainty—and machine learning is all about making decisions under uncertainty. This article demystifies the probabilistic foundations that underpin everything from spam filters to large language models.
Calculus for ML: Gradients, Optimization and the Chain rule
If linear algebra provides the vocabulary of machine learning, calculus provides the grammar—it tells us how things change. This article demystifies the calculus concepts that power modern ML