0PricingLogin▼
Deep Learning Academy · Lesson

Gradients Point Uphill — So Step the Other Way

Using the slope to improve weights.

Reading the Slope

To walk downhill you first need to know which way is down. The gradient is the tool that tells you the slope of the loss at your current spot.

Gradient Points Uphill

Here is the surprise: the gradient points in the direction where loss increases fastest. It shows you the steepest way up, not down.

All lessons in this course

  1. Loss as a Landscape to Descend
  2. Gradients Point Uphill — So Step the Other Way
  3. Learning Rate: Too Big, Too Small, Just Right
  4. Minimize a Function by Hand in Python
← Back to Deep Learning Academy