Index Ai Academy
Glossary · Phase 2 · Math for ML engineers

vector-Jacobian product

What backpropagation computes at each step: the incoming gradient times the layer's Jacobian, without ever building the Jacobian.

Try it now

Learn it properly

The chain rule with vectors · Derivatives of functions inside functions: the heart of backprop. About 40 minutes.

Other terms from the same lesson

  • chain rule: To find how a chain of steps responds to a nudge, multiply how much each step responds.
  • target: The right answer a model should give for an example, such as the true sale amount. The loss measures how far the prediction is from it.
Keep learning

More in plain English.

1286 terms in the glossary, each with the lesson that teaches it.

1286 terms

The glossary

Every word you'll meet in AI and machine learning, explained in everyday language.

Phase 2 · lesson 40 min

The chain rule with vectors

Derivatives of functions inside functions: the heart of backprop.

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