(PECL fann >= 1.0.0) Returns the sarprop temperature float fann_get_sarprop_temperature ( resource $ann ) Returns the sarprop temperature. The default temperature is 0.015. Parameters: ann Neural network resource. Returns: The sarprop temperature, or FALSE on error. See also:

(PECL fann >= 1.0.0) Returns the sarprop step error threshold factor float fann_get_sarprop_step_error_threshold_factor ( resource $ann ) The sarprop step error threshold factor. The default factor is 0.1. Parameters: ann Neural network resource. Returns: The sarprop step error threshold factor, or FALSE on error.

(PECL fann >= 1.0.0) Returns the sarprop step error shift float fann_get_sarprop_step_error_shift ( resource $ann ) Returns the sarprop step error shift. The default step error shift is 1.385. Parameters: ann Neural network resource. Returns: The sarprop step error shift , or FALSE on error.

(PECL fann >= 1.0.0) Returns the increase factor used during RPROP training float fann_get_rprop_increase_factor ( resource $ann ) The increase factor is a value larger than 1, which is used to increase the step-size during RPROP training. The default increase factor is 1.2. Parameters: ann Neural network resource. Returns: The increase factor

(PECL fann >= 1.0.0) Returns the initial step-size ReturnType fann_get_rprop_delta_zero ( resource $ann ) The initial step-size is a positive number determining the initial step size. The default delta zero is 0.1. Parameters: ann Neural network resource. Returns: The initial step-size, or FALSE on error.

(PECL fann >= 1.0.0) Returns the minimum step-size float fann_get_rprop_delta_min ( resource $ann ) The minimum step-size is a small positive number determining how small the minimum step-size may be. The default value delta min is 0.0. Parameters: ann Neural network resource. Returns: The minimum step-size, or FALSE on error.

(PECL fann >= 1.0.0) Returns the maximum step-size float fann_get_rprop_delta_max ( resource $ann ) The maximum step-size is a positive number determining how large the maximum step-size may be. The default delta max is 50.0. Parameters: ann Neural network resource. Returns: The maximum step-size, or FALSE on error.

(PECL fann >= 1.0.0) Returns the increase factor used during RPROP training float fann_get_rprop_decrease_factor ( resource $ann ) The decrease factor is a value smaller than 1, which is used to decrease the step-size during RPROP training. The default decrease factor is 0.5. Parameters: ann Neural network resource. Returns: The decrease facto

(PECL fann >= 1.0.0) Returns the mu factor float fann_get_quickprop_mu ( resource $ann ) The mu factor is used to increase and decrease the step-size during quickprop training. The mu factor should always be above 1, since it would otherwise decrease the step-size when it was suppose to increase it. The default mu factor is 1.75. Parameters: ann Neural network resourc

(PECL fann >= 1.0.0) Returns the decay which is a factor that weights should decrease in each iteration during quickprop training float fann_get_quickprop_decay ( resource $ann ) The decay is a small negative valued number which is a factor that the weights should decrease in each iteration during quickprop training. This is used to make sure that the weights do not become too high during training. The default decay is