Backpropagation

Feb 7, 2026 ML Math Derivations 32 min read

ML Math Derivations (19): Neural Networks and Backpropagation

How does a neural network learn? This article derives forward propagation, the chain rule mechanics of backpropagation, vanishing/exploding gradients, and initialization strategies (Xavier, He).

Mar 12, 2025 Linear Algebra 30 min read

Essence of Linear Algebra (11): Matrix Calculus and Optimization — The Engine Behind Machine Learning

Adjusting the shower temperature is a tiny version of training a neural network: you change a parameter based on an error signal. Matrix calculus is the language that scales this idea to millions of parameters, and …