[source] # He The He initializer was designed to initialize parameters that feed into rectified [Activation](../hidden-layers/activation.md) layers such as those employing [ReLU](../activation-functions/relu.md), [Leaky ReLU](../activation-functions/leaky-relu.md), or [ELU](../activation-functions/elu.md). It draws values from a uniform distribution with limits defined as +/- (6 / (fanIn + fanOut)) ** (1. / sqrt(2)). ## Parameters This initializer does not have any parameters. ## Example ```php use Rubix\ML\NeuralNet\Initializers\He; $initializer = new He(); ``` ## References [^1]: K. He et al. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.