/profile.jpeg

Wassim Seifeddine

[ARCHIVE] Using Tensorflow Gradient Descent to minimize functions

You probably heard the hype around Gradient Descent & how it’s used to optimize Deep Learning Models. But you may never knew that it can be used to minimize ANY function you know.

In this blog post we’re going to see how to use Gradient Descent to optimize a simple quadratic function

we all know from highschool.

$ax^2 + bx + c$

with
a = 1
b = -40
c = 400

we get the following formula