Stochastic#
A constant learning rate optimizer based on vanilla Stochastic Gradient Descent.
Parameters#
| # | Name | Default | Type | Description |
|---|---|---|---|---|
| 1 | rate | 0.01 | float | The learning rate that controls the global step size. |
Example#
use Rubix\ML\NeuralNet\Optimizers\Stochastic;
$optimizer = new Stochastic(0.01);
Last update: 2021-01-23