Glossary · Phase 2 · Math, when you need it
Gradient descent
Improving a model by taking small steps in the direction that lowers the error the most, over and over.
Try it now
This is the bowl from the worked example. Press Step a few times at 0.1. Then try 0.9: it bounces across the valley but still settles. Then try 1.05: each step overshoots further, and it flies off (diverges).
Learn it properly
Optimization by walking downhill · Repeatedly step against the gradient to find a minimum. About 30 minutes.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.