ml-glossary

Why we included this project

Most people who read ML papers end up chasing a term through a few blog posts and a Stack Overflow thread before it clicks. This glossary puts the plain-language definition, a citation to the original paper or tutorial, and often a NumPy snippet or diagram in the same entry, so the intuition and the implementation sketch live side by side. It covers the usual territory, activation functions, loss functions, and applications, and the community editing process keeps entries accurate and current. Students prepping for interviews, engineers brushing up before a project, and anyone who needs a reliable citation in a hurry will find it useful. It is a reference to read rather than software to deploy, and that is the point: the value is in how fast it gets you unstuck.