A | |
activation_function_enum, FANN | |
C | |
callback_type, FANN | |
Cascade Training | |
cascadetrain_on_data, neural_net | |
cascadetrain_on_file, neural_net | |
clear_scaling_params, neural_net | |
connection, FANN | |
copy_from_struct_fann, neural_net | |
create_from_file, neural_net | |
create_shortcut, neural_net | |
create_shortcut_array, neural_net | |
create_sparse, neural_net | |
create_sparse_array, neural_net | |
create_standard, neural_net | |
create_standard_array, neural_net | |
create_train_from_callback, training_data | |
Creation,Destruction&Execution | |
D | |
descale_input, neural_net | |
descale_output, neural_net | |
descale_train, neural_net | |
destroy | |
E | |
Enumerations, FANN | |
Enumerations and Constants | |
Error Handling | |
error_function_enum, FANN | |
ERRORFUNC_LINEAR, FANN | |
ERRORFUNC_TANH, FANN |
Trains on an entire dataset, for a period of time using the Cascade2 training algorithm.
void cascadetrain_on_data( const training_data & data, unsigned int max_neurons, unsigned int neurons_between_reports, float desired_error )
Does the same as cascadetrain_on_data, but reads the training data directly from a file.
void cascadetrain_on_file( const std:: string & filename, unsigned int max_neurons, unsigned int neurons_between_reports, float desired_error )
Clears scaling parameters.
bool clear_scaling_params()
Set the internal fann struct to a copy of other
void copy_from_struct_fann( struct fann * other )
Constructs a backpropagation neural network from a configuration file, which have been saved by save.
bool create_from_file( const std:: string & configuration_file )
Creates a standard backpropagation neural network, which is not fully connected and which also has shortcut connections.
bool create_shortcut( unsigned int num_layers, ... )
Just like create_shortcut, but with an array of layer sizes instead of individual parameters.
bool create_shortcut_array( unsigned int num_layers, const unsigned int * layers )
Creates a standard backpropagation neural network, which is not fully connected.
bool create_sparse( float connection_rate, unsigned int num_layers, ... )
Just like create_sparse, but with an array of layer sizes instead of individual parameters.
bool create_sparse_array( float connection_rate, unsigned int num_layers, const unsigned int * layers )
Creates a standard fully connected backpropagation neural network.
bool create_standard( unsigned int num_layers, ... )
Just like create_standard, but with an array of layer sizes instead of individual parameters.
bool create_standard_array( unsigned int num_layers, const unsigned int * layers )
Creates the training data struct from a user supplied function.
void create_train_from_callback( unsigned int num_data, unsigned int num_input, unsigned int num_output, void (FANN_API *user_function)( unsigned int, unsigned int, unsigned int, fann_type * , fann_type * ) )
Scale data in input vector after get it from ann based on previously calculated parameters.
void descale_input( fann_type * input_vector )
Scale data in output vector after get it from ann based on previously calculated parameters.
void descale_output( fann_type * output_vector )
Descale input and output data based on previously calculated parameters.
void descale_train( training_data & data )
Destructs the entire network.
void destroy()
Destructs the training data.
void destroy_train()