« fann_get_activation_function
fann_get_bias_array »

fann_get_activation_steepness

(PECL fann >= 1.0.0)

fann_get_activation_steepness — Returns the activation steepness for supplied neuron and layer number

説明

function fann_get_activation_steepness(resource $ann, int $layer, int $neuron): float

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

It is not possible to get 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.

パラメータ

ann

ニューラルネットワークリソース。

layer

Layer number

neuron

Neuron number

戻り値

The activation steepness for the neuron or -1 if the neuron is not defined in the neural network, or false on error.

参考

関連キーワード:
activation   steepness   layer   neuron   fann   number   supplied   Sets   neurons   output   input   training   neural   hidden   bias   Fann   resource   float   counting   says   something   about   fast   goes   minimum
関連する関数・ページ:
function.fann-set-activation-steepness   function.fann-set-activation-steepness-layer   function.fann-set-activation-steepness-output   function.fann-get-activation-function   function.fann-set-activation-function   function.fann-set-activation-steepness-hidden