fann_set_activation_steepness

(PECL fann >= 1.0.0)

fann_set_activation_steepnessSets the activation steepness for supplied neuron and layer number

Description

fann_set_activation_steepness(
    resource $ann,
    float $activation_steepness,
    int $layer,
    int $neuron
): bool

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 aggressive 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.

Return Values

Returns true on success, or false otherwise.

See Also

add a note

User Contributed Notes

There are no user contributed notes for this page.
To Top