XOR (异或)训练

以下例子展示了怎么训练数据来实现 XOR (异或)功能。

Example #1 xor.data file

4 2 1
-1 -1
-1
-1 1
1
1 -1
1
1 1
-1

Example #2 一般训练

<?php
$num_input 
2;
$num_output 1;
$num_layers 3;
$num_neurons_hidden 3;
$desired_error 0.001;
$max_epochs 500000;
$epochs_between_reports 1000;

$ann fann_create_standard($num_layers$num_input$num_neurons_hidden$num_output);

if (
$ann) {
    
fann_set_activation_function_hidden($annFANN_SIGMOID_SYMMETRIC);
    
fann_set_activation_function_output($annFANN_SIGMOID_SYMMETRIC);

    
$filename dirname(__FILE__) . "/xor.data";
    if (
fann_train_on_file($ann$filename$max_epochs$epochs_between_reports$desired_error))
        
fann_save($anndirname(__FILE__) . "/xor_float.net");

    
fann_destroy($ann);
}
?>

这个例子展示怎么读取神经网络并且使用 XOR (异或)功能来运行数据。

Example #3 一般测试

<?php
$train_file 
= (dirname(__FILE__) . "/xor_float.net");
if (!
is_file($train_file))
    die(
"The file xor_float.net has not been created! Please run simple_train.php to generate it");

$ann fann_create_from_file($train_file);
if (!
$ann)
    die(
"ANN could not be created");

$input = array(-11);
$calc_out fann_run($ann$input);
printf("xor test (%f,%f) -> %f\n"$input[0], $input[1], $calc_out[0]);
fann_destroy($ann);
?>

User Contributed Notes

ithirzty 25-Nov-2019 07:44
If you wan't your result to be saved after the time limit, you will need to add this to your code.
<?php
function shutdown()
{
  global
$ann;
fann_save($ann, dirname(__FILE__) . "/result.net");
fann_destroy($ann);
}

register_shutdown_function('shutdown');
?>
where $ann is your neural network var and 'result.net' your neural network config file.
Ray.Paseur sometimes uses Gmail 03-Mar-2017 08:43
A helpful reference for FANN is available here:
http://leenissen.dk/fann/html/files2/theory-txt.html
Aurelien Marchand 08-May-2015 02:08
Here is an explanation for the input file for training, as it might be obvious to everyone and you must understand it to write your own:

4 2 1 <- header file saying there are 4 sets to read, with 2 inputs and 1 output
-1 -1 <- the 2 inputs for the 1st group
-1    <- the 1 output for the 1st group
-1 1  <- the 2 inputs for the 2nd group
1     <- the 1 output for the 2nd group
1 -1  <- the 2 inputs for the 3rd group
1     <- the 1 output for the 3rd group
1 1   <- the 2 inputs for the 4th group
-1    <- the 1 output for the 4th group