tf.nn.leaky_relu

TensorFlow 1 version View source on GitHub

Compute the Leaky ReLU activation function.

tf.nn.leaky_relu(
    features, alpha=0.2, name=None
)

Source: Rectifier Nonlinearities Improve Neural Network Acoustic Models. AL Maas, AY Hannun, AY Ng - Proc. ICML, 2013. Args: features: A Tensor representing preactivation values. Must be one of the following types: float16, float32, float64, int32, int64. alpha: Slope of the activation function at x < 0. name: A name for the operation (optional).

The activation value.

References:

Rectifier Nonlinearities Improve Neural Network Acoustic Models: Maas et al., 2013 (pdf)