User Tools

Site Tools


neurali:libfann2

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
neurali:libfann2 [2015/01/29 22:27]
profpro
neurali:libfann2 [2020/06/08 22:20] (current)
Line 1: Line 1:
 +====== Libfann2 ======
  
 +{{:neurali:italian-flag.png?nolink&25|}} > [[neurali:libfann_it]]
 +
 +{{:neurali:flag-of-britain-1.png?nolink&100|}}
 +
 +===== Data types =====
 +  * //struct fann//, which represents an artificial neural network
 +  * //struct fann_train_data//, which represent training data.
 +  * //fann_type//, is the type used for the weights, inputs and outputs
 +  * //fann_connection//, is the type which Describes a connection between two neurons and its weight
 +
 +===== Funzioni =====
 +FANN Creation/Execution The FANN library is designed to be very easy to use.
 +
 +==== Creation, Destruction & Execution ====
 +
 +  - fann_create_standard Creates a standard fully connected backpropagation neural network.
 +  - fann_create_standard_array Just like fann_create_standard, but with an array of layer sizes instead of individual parameters.
 +  - fann_create_sparse Creates a standard backpropagation neural network, which is not fully connected.
 +  - fann_create_sparse_array Just like fann_create_sparse, but with an array of layer sizes instead of individual parameters.
 +  - fann_create_shortcut Creates a standard backpropagation neural network, which is not fully connected and which also has shortcut connections.
 +  - fann_create_shortcut_array Just like fann_create_shortcut, but with an array of layer sizes instead of individual parameters.
 +  - fann_destroy Destroys the entire network and properly freeing all the associated memmory.
 +  - fann_run Will run input through the neural network, returning an array of outputs, the number of which being equal to the number of neurons in the output layer.
 +  - fann_randomize_weights Give each connection a random weight between min_weight and max_weight
 +  - fann_init_weights Initialize the weights using Widrow + Nguyen’s algorithm.
 +  - fann_print_connections Will print the connections of the ann in a compact matrix, for easy viewing of the internals of the ann.
 +
 +==== Parameters ====
 +
 +  * fann_print_parameters Prints all of the parameters and options of the ANN
 +  * fann_get_num_input Get the number of input neurons.
 +  * fann_get_num_output Get the number of output neurons.
 +  * fann_get_total_neurons Get the total number of neurons in the entire network.
 +  * fann_get_total_connections Get the total number of connections in the entire network.
 +  * fann_get_network_type Get the type of neural network it was created as.
 +  * fann_get_connection_rate Get the connection rate used when the network was created
 +  * fann_get_num_layers Get the number of layers in the network
 +  * fann_get_layer_array Get the number of neurons in each layer in the network.
 +  * fann_get_bias_array Get the number of bias in each layer in the network.
 +  * fann_get_connection_array Get the connections in the network.
 +  * fann_set_weight_array Set connections in the network.
 +  * fann_set_weight Set a connection in the network.
 +  * fann_set_user_data Store a pointer to user defined data.
 +  * fann_get_user_data Get a pointer to user defined data that was previously set with fann_set_user_data.
 +  * fann_get_decimal_point Returns the position of the decimal point in the ann.
 +  * fann_get_multiplier returns the multiplier that fix point data is multiplied with.
neurali/libfann2.txt · Last modified: 2020/06/08 22:20 (external edit)