The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
Drawing a value so that each factor of ten is equally likely, by drawing its exponent evenly. Used for learning rates and regularization strengths.
Each new setting multiplies the bill. Each new value raises the base.
Hyperparameter search · What a grid costs, random search on a log scale, stopping weak settings early, and why the winner's validation score flatters it. About 40 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
What a grid costs, random search on a log scale, stopping weak settings early, and why the winner's validation score flatters it.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write