Skip to content

Latest commit

 

History

History
17 lines (12 loc) · 795 Bytes

File metadata and controls

17 lines (12 loc) · 795 Bytes

[source]

Xavier 1

The Xavier 1 initializer draws from a uniform distribution [-limit, limit] where limit is equal to sqrt(6 / (fanIn + fanOut)). This initializer is best suited for layers that feed into an activation layer that outputs a value between 0 and 1 such as Softmax or Sigmoid.

Parameters

This initializer does not have any parameters.

Example

use Rubix\ML\NeuralNet\Initializers\XavierNormal;

$initializer = new XavierNormal();

References