struct fann

Properties

unsigned int errno_f

The type of error that last occured.

FILE * error_log

Where to log error messages.

char * errstr

A string representation of the last error.

float learning_rate

The learning rate of the network.

float connection_rate

The connection rate of the network. Between 0 and 1, 1 meaning fully connected.

struct fann_layer * first_layer

Pointer to the first layer (input layer) in an array af all the layers, including the input and output layers.

struct fann_layer * last_layer

Pointer to the layer past the last layer in an array af all the layers, including the input and output layers.

unsigned int total_neurons

Total number of neurons. Very useful, because the actual neurons are allocated in one long array.

unsigned int num_input

Number of input neurons (not calculating bias)

unsigned int num_output

Number of output neurons (not calculating bias)

fann_type * train_deltas

Used to contain the error deltas used during training Is allocated during first training session, which means that if we do not train, it is never allocated.

unsigned int activation_function_output

Used to choose which activation function to use in the output layer.

unsigned int activation_function_hidden

Used to choose which activation function to use in the hidden layers.

unsigned int activation_hidden_steepness

Parameters for the activation function in the hidden layers.

unsigned int activation_output_steepness

Parameters for the activation function in the output layer.

unsigned int decimal point

Fixed point only.The decimal point, used for shifting the fix point in fixed point integer operatons.

unsigned int multiplier

Fixed point only.The multiplier, used for multiplying the fix point in fixed point integer operatons. Only used in special cases, since the decimal_point is much faster.

fann_type * activation_hidden_results

An array of six members used by some activation functions to hold results for the hidden layer(s).

fann_type * activation_hidden_values

An array of six members used by some activation functions to hold values for the hidden layer(s).

fann_type * activation_output_results

An array of six members used by some activation functions to hold results for the output layer.

fann_type * activation_output_values

An array of six members used by some activation functions to hold values for the output layer.

unsigned int total_connections

Total number of connections. Very useful, because the actual connections are allocated in one long array.

fann_type * output

Used to store outputs in.

unsigned int num_errors

The number of data used to calculate the error.

float error_value

The total error value. The real mean square error is error_value/num_errors.