Please note -> ALLfann scaling related functions are not functional.
They are implemented wrong so the scaling is calculated within the library but it's not referenced back to the input variables.
(PECL fann >= 1.0.0)
fann_scale_input — 在以前计算参数的基础上，在训练之前放大输入向量中的数据
$ann
, array $input_vector
)在以前计算参数的基础上，在训练之前放大输入向量中的数据。
annNeural network resource.
input_vector将要被缩放的输入向量。
Returns TRUE on success, or FALSE otherwise.
Please note -> ALLfann scaling related functions are not functional.
They are implemented wrong so the scaling is calculated within the library but it's not referenced back to the input variables.