Signing you in…

Gradient descent: optimization in high dimensions

Gradient descent: walking downhill in the fog

Imagine standing on a mountain in thick fog. You only see the ground at your feet — the slope at this spot. Goal: reach the valley. Strategy: take a step where the ground goes down. Repeat. That is gradient descent. Loss is the mountain. Model weights are your coordinates. The gradient is the slope underfoot. The aim is to find the bottom.

Content is available with subscription.
Get full access to all courses on the platform for one year with a single payment.
Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.