Skip to content

Gradient descent #
Find similar titles

Gradient descent (경사 하강법, Steepest descent) is a first-order iterative optimization algorithm for finding the minimum of a function. (https://en.wikipedia.org/wiki/Gradient_descent)

Gradient descent는 함수의 극대, 극소를 찾는 방법이고, Newton's method는 함수값이 0이 되는 해를 찾는 방법이다.

Suggested Pages #

web biohackers.net
0.0.1_20140628_0