A fast way for computers to find derivatives automatically.
Autodiff is like Google Maps for a marble on a hill. It points downhill fast, so the marble stops acting lost.
It finds gradients during neural network training. Then the optimizer uses them to update parameters.
Backpropagation
Backprop sends errors backward and uses autodiff to find derivatives fast.
Parameter
Autodiff finds gradients, and those gradients guide each parameter change.
SGD
SGD needs gradients from autodiff before it can update parameters.
Framework
Modern frameworks usually have autodiff built in.