Gradient

upshard

\nabla f = \left( \frac{\partial f}{\partial x_1}, \dots, \frac{\partial f}{\partial x_n} \right)

The vector of all the partial derivatives, pointing in the direction of steepest increase. Training walks against it, which is the whole of what "descent" means.

Symbols

$\nabla$: The gradient operator, read as del or nabla.
$\partial$: A partial derivative — vary one input, hold the rest.
$f$: A function of many variables returning one number.

Save your progress

Your account

Delete your account?

Gradient

Keyboard shortcuts