fann_create_sparse

(PECL fann >= 1.0.0)

fann_create_sparse — Creates a standard backpropagation neural network, which is not fully connected

Description

fann_create_sparse ( float $connection_rate , int $num_layers , int $num_neurons1 , int $num_neurons2 [, int $... ] ) : resource

Creates a standard backpropagation neural network, which is not fully connected.

Parameters

connection_rate

The connection rate controls how many connections there will be in the network. If the connection rate is set to 1, the network will be fully connected, but if it is set to 0.5 only half of the connections will be set. A connection rate of 1 will yield the same result as fann_create_standard().

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.

Return Values

Returns a neural network resource on success, or FALSE on error.

See Also

  • fann_create_sparse_array() - Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes
  • fann_create_standard() - Creates a standard fully connected backpropagation neural network
  • fann_create_shortcut() - Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections