fann_create_shortcut
(PECL fann >= 1.0.0)
fann_create_shortcut — Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections
Description
$num_layers
, int $num_neurons1
, int $num_neurons2
[, int $...
] )Creates a standard backpropagation neural network, which is not fully connected and which also has shortcut connections.
Shortcut connections are connections that skip layers. A fully connected network with shortcut connections, is a network where all neurons are connected to all neurons in later layers. Including direct connections from the input layer to the output layer.
Liste de paramètres
-
num_layers -
The total number of layers including the input and the output layer.
-
num_neurons1 -
Number of neurons in the first layer.
-
num_neurons2 -
Number of neurons in the second layer.
-
... -
Number of neurons in other layers.
Valeurs de retour
Returns a neural network resource on success, or FALSE on error.
Voir aussi
- fann_create_shortcut_array() - Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections
- fann_create_sparse() - Creates a standard backpropagation neural network, which is not fully connected
- fann_create_standard() - Creates a standard fully connected backpropagation neural network
