Search results
We did not find results for: gradient descent.
Check spelling or type a new query.
We did not find results for: gradient descent.
Check spelling or type a new query.
Gradient descent is a method for unconstrained mathematical optimization. It is a iterative algorithm for finding a local minimum of a differentiable multivariate function. The idea is to take repeated steps in the opposite direction of the gradient (or approximate gradient) of the function at the current point, because this is the direction of steepest descent. Wikipedia