Thresholded ReLU#
A version of the ReLU function that activates only if the input is above some user-specified threshold level.
Parameters#
# | Name | Default | Type | Description |
---|---|---|---|---|
1 | threshold | 1.0 | float | The threshold at which the neuron is activated. |
Example#
use Rubix\ML\NeuralNet\ActivationFunctions\ThresholdedReLU;
$activationFunction = new ThresholdedReLU(0.5);
References#
-
K. Konda et al. (2015). Zero-bias autoencoders and the benefits of co-adapting features. ↩
Last update:
2021-03-03