« fann_create_sparse
fann_create_standard »

fann_create_sparse_array

(PECL fann >= 1.0.0)

fann_create_sparse_array — Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes

説明

function fann_create_sparse_array(float $connection_rate, int $num_layers, array $layers): resource

Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes.

パラメータ

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.

layers

An array of layer sizes.

戻り値

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

参考

  • 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
  • fann_create_shortcut() - Creates a standard backpropagation neural network which is not fully connected and has shortcut connections

関連キーワード:
standard   network   fann   create   neural   fully   connected   Creates   backpropagation   layer   sizes   sparse   connection   rate   layers   using   connections   resource   shortcut   Fann   float   controls   many   there   half
関連する関数・ページ:
function.fann-create-sparse   function.fann-create-standard-array   function.fann-create-standard   function.fann-create-shortcut-array   function.fann-create-shortcut   book.fann