0Pricing
Deep Learning Academy · Lesson

Learning Rate: Too Big, Too Small, Just Right

The single most important knob.

The Size of Your Step

The gradient tells you which way to go, but how far? The learning rate is the multiplier that sets how big each downhill step is.

w = w - lr * grad

A Single Powerful Knob

The learning rate is often the single most important setting in training. Get it wrong and even a perfect model will fail to learn.

lr = 0.01

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