fann_set_activation_steepness

(PECL fann >= 1.0.0)
Sets the activation steepness for supplied neuron and layer number
bool fann_set_activation_steepness ( resource $ann, float $activation_steepness, int $layer, int $neuron )

Set the activation steepness for neuron number neuron in layer number layer, counting the input layer as layer 0.

It is not possible to set activation steepness for the neurons in the input layer.

The steepness of an activation function says something about how fast the activation function goes from the minimum to the maximum. A high value for the activation function will also give a more agressive training.

When training neural networks where the output values should be at the extremes (usually 0 and 1, depending on the activation function), a steep activation function can be used (e.g. 1.0).

The default activation steepness is 0.5.

Parameters:
ann

Neural network resource.

activation_steepness

The activation steepness.

layer

Layer number.

neuron

Neuron number.

Returns:

Returns TRUE on success, or FALSE otherwise.

See also:

fann_set_activation_steepness_layer() -

fann_set_activation_steepness_hidden() -

fann_set_activation_steepness_output() -

fann_get_activation_steepness() -

fann_set_activation_function() -

doc_php
2016-02-24 16:05:56
Comments
Leave a Comment

Please login to continue.