Start learning →

Simulators

Gradient descent simulator

The points and the current line are on the left, and the loss after each step on the right. Each step moves the line's slope and intercept a little downhill on the loss.

The simulator

Gradient descent simulator: how to use it

Change the learning rate and run it again: a rate too small crawls towards the best line, and one too large makes the loss explode.

Lessons that use it

  • Gradient descent (Machine Learning)Train a model by walking downhill on its loss: the gradient, the update rule, the learning rate, and batch, stochastic and mini-batch gradient descent.

See also