This section includes enums and helper data types used by the two main classes neural_net and training_data
FANN C++ Datatypes | This section includes enums and helper data types used by the two main classes neural_net and training_data |
Types | |
fann_type | fann_type is the type used for the weights, inputs and outputs of the neural network. |
Enumerations | |
error_function_enum | Error function used during training. |
stop_function_enum | Stop criteria used during training. |
training_algorithm_enum | The Training algorithms used when training on training_data with functions like neural_net::train_on_data or neural_net::train_on_file. |
activation_function_enum | The activation functions used for the neurons during training. |
network_type_enum | Definition of network types used by neural_net::get_network_type |
Types | |
connection | Describes a connection between two neurons and its weight |
callback_type | This callback function can be called during training when using neural_net::train_on_data, neural_net::train_on_file or neural_net::cascadetrain_on_data. |
fann_type is the type used for the weights, inputs and outputs of the neural network.
float | if you include fann.h or floatfann.h |
double | if you include doublefann.h |
int | if you include fixedfann.h (please be aware that fixed point usage is only to be used during execution, and not during training). |
Error function used during training.
neural_net::set_train_error_function, neural_net::get_train_error_function
Stop criteria used during training.
STOPFUNC_MSE | Stop criteria is Mean Square Error (MSE) value. |
STOPFUNC_BIT | Stop criteria is number of bits that fail. The number of bits; means the number of output neurons which differ more than the bit fail limit (see neural_net::get_bit_fail_limit, neural_net::set_bit_fail_limit). The bits are counted in all of the training data, so this number can be higher than the number of training data. |
neural_net::set_train_stop_function, neural_net::get_train_stop_function
The Training algorithms used when training on training_data with functions like neural_net::train_on_data or neural_net::train_on_file. The incremental training looks alters the weights after each time it is presented an input pattern, while batch only alters the weights once after it has been presented to all the patterns.
TRAIN_INCREMENTAL | Standard backpropagation algorithm, where the weights are updated after each training pattern. This means that the weights are updated many times during a single epoch. For this reason some problems, will train very fast with this algorithm, while other more advanced problems will not train very well. |
TRAIN_BATCH | Standard backpropagation algorithm, where the weights are updated after calculating the mean square error for the whole training set. This means that the weights are only updated once during an epoch. For this reason some problems, will train slower with this algorithm. But since the mean square error is calculated more correctly than in incremental training, some problems will reach a better solutions with this algorithm. |
TRAIN_RPROP | A more advanced batch training algorithm which achieves good results for many problems. The RPROP training algorithm is adaptive, and does therefore not use the learning_rate. Some other parameters can however be set to change the way the RPROP algorithm works, but it is only recommended for users with insight in how the RPROP training algorithm works. The RPROP training algorithm is described by [Riedmiller and Braun, 1993], but the actual learning algorithm used here is the iRPROP- training algorithm which is described by [Igel and Husken, 2000] which is a variant of the standard RPROP training algorithm. |
TRAIN_QUICKPROP | A more advanced batch training algorithm which achieves good results for many problems. The quickprop training algorithm uses the learning_rate parameter along with other more advanced parameters, but it is only recommended to change these advanced parameters, for users with insight in how the quickprop training algorithm works. The quickprop training algorithm is described by [Fahlman, 1988]. |
FANN_TRAIN_SARPROP | THE SARPROP ALGORITHM: A SIMULATED ANNEALING ENHANCEMENT TO RESILIENT BACK PROPAGATION http://citeseerx.ist.psu.edu |
neural_net::set_training_algorithm, neural_net::get_training_algorithm
The activation functions used for the neurons during training. The activation functions can either be defined for a group of neurons by neural_net::set_activation_function_hidden and neural_net::set_activation_function_output or it can be defined for a single neuron by neural_net::set_activation_function.
The steepness of an activation function is defined in the same way by neural_net::set_activation_steepness_hidden, neural_net::set_activation_steepness_output and neural_net::set_activation_steepness.
FANN_LINEAR | Linear activation function. |
FANN_THRESHOLD | Threshold activation function. |
FANN_THRESHOLD_SYMMETRIC | Threshold activation function. |
FANN_SIGMOID | Sigmoid activation function. |
FANN_SIGMOID_STEPWISE | Stepwise linear approximation to sigmoid. |
FANN_SIGMOID_SYMMETRIC | Symmetric sigmoid activation function, aka. tanh. |
FANN_SIGMOID_SYMMETRIC | Stepwise linear approximation to symmetric sigmoid. |
FANN_GAUSSIAN | Gaussian activation function. |
FANN_GAUSSIAN_SYMMETRIC | Symmetric gaussian activation function. |
FANN_ELLIOT | Fast (sigmoid like) activation function defined by David Elliott |
FANN_ELLIOT_SYMMETRIC | Fast (symmetric sigmoid like) activation function defined by David Elliott |
FANN_LINEAR_PIECE | Bounded linear activation function. |
FANN_LINEAR_PIECE_SYMMETRIC | Bounded Linear activation function. |
FANN_SIN_SYMMETRIC | Periodical sinus activation function. |
FANN_COS_SYMMETRIC | Periodical cosinus activation function. |
neural_net::set_activation_function_hidden, neural_net::set_activation_function_output
Definition of network types used by neural_net::get_network_type
LAYER | Each layer only has connections to the next layer |
SHORTCUT | Each layer has connections to all following layers |
neural_net::get_network_type, fann_get_network_type
This enumeration appears in FANN >= 2.1.0
Describes a connection between two neurons and its weight
from_neuron | Unique number used to identify source neuron |
to_neuron | Unique number used to identify destination neuron |
weight | The numerical value of the weight |
neural_net::get_connection_array, neural_net::set_weight_array
This structure appears in FANN >= 2.1.0
This callback function can be called during training when using neural_net::train_on_data, neural_net::train_on_file or neural_net::cascadetrain_on_data.
typedef int (*callback_type) (neural_net &net, training_data &train, unsigned int max_epochs, unsigned int epochs_between_reports, float desired_error, unsigned int epochs, void *user_data);
The callback can be set by using neural_net::set_callback and is very useful for doing custom things during training. It is recommended to use this function when implementing custom training procedures, or when visualizing the training in a GUI etc. The parameters which the callback function takes is the parameters given to the neural_net::train_on_data, plus an epochs parameter which tells how many epochs the training have taken so far.
The callback function should return an integer, if the callback function returns -1, the training will terminate.
int print_callback(FANN::neural_net &net, FANN::training_data &train, unsigned int max_epochs, unsigned int epochs_between_reports, float desired_error, unsigned int epochs, void *user_data) { cout << "Epochs " << setw(8) << epochs << ". " << "Current Error: " << left << net.get_MSE() << right << endl; return 0; }
neural_net is the main neural network class used for both training and execution
class neural_net
training_data is used to create and manipulate training data used by the neural_net
class training_data
Trains on an entire dataset, for a period of time.
void train_on_data( const training_data & data, unsigned int max_epochs, unsigned int epochs_between_reports, float desired_error )
Does the same as train_on_data, but reads the training data directly from a file.
void train_on_file( const std:: string & filename, unsigned int max_epochs, unsigned int epochs_between_reports, float desired_error )
Get the type of neural network it was created as.
network_type_enum get_network_type()
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 )
Set the error function used during training.
void set_train_error_function( error_function_enum train_error_function )
Returns the error function used during training.
error_function_enum get_train_error_function()
Returns the bit fail limit used during training.
fann_type get_bit_fail_limit()
Set the bit fail limit used during training.
void set_bit_fail_limit( fann_type bit_fail_limit )
Set the stop function used during training.
void set_train_stop_function( stop_function_enum train_stop_function )
Returns the the stop function used during training.
stop_function_enum get_train_stop_function()
Set the training algorithm.
void set_training_algorithm( training_algorithm_enum training_algorithm )
Return the training algorithm as described by FANN::training_algorithm_enum.
training_algorithm_enum get_training_algorithm()
Set the activation function for all of the hidden layers.
void set_activation_function_hidden( activation_function_enum activation_function )
Set the activation function for the output layer.
void set_activation_function_output( activation_function_enum activation_function )
Set the activation function for neuron number neuron in layer number layer, counting the input layer as layer 0.
void set_activation_function( activation_function_enum activation_function, int layer, int neuron )
Set the steepness of the activation steepness in all of the hidden layers.
void set_activation_steepness_hidden( fann_type steepness )
Set the steepness of the activation steepness in the output layer.
void set_activation_steepness_output( fann_type steepness )
Set the activation steepness for neuron number neuron in layer number layer, counting the input layer as layer 0.
void set_activation_steepness( fann_type steepness, int layer, int neuron )
Get the type of neural network it was created as.
FANN_EXTERNAL enum fann_nettype_enum FANN_API fann_get_network_type( struct fann * ann )
Get the connections in the network.
void get_connection_array( connection * connections )
Set connections in the network.
void set_weight_array( connection * connections, unsigned int num_connections )
Sets the callback function for use during training.
void set_callback( callback_type callback, void * user_data )