fann_create_standard

(PECL fann >= 1.0.0)

fann_create_standardCreates a standard fully connected backpropagation neural network

説明

fann_create_standard ( int $num_layers , int $num_neurons1 , int $num_neurons2 [, int $... ] ) : resource

Creates a standard fully connected backpropagation neural network.

There will be a bias neuron in each layer (except the output layer), and this bias neuron will be connected to all neurons in the next layer. When running the network, the bias nodes always emits 1.

To destroy a neural network use the fann_destroy() function.

パラメータ

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.

返り値

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

参考

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