(PECL fann >= 1.0.0) Resets the mean square error from the network

(PECL fann >= 1.0.0) Shuffles training data, randomizing the order

(PECL fann >= 1.0.0) Creates a standard backpropagation neural network which is not fully connectected and

(PECL fann >= 1.0.0) Destroys the entire network and properly freeing all the associated memory

(PECL fann >= 1.0.0) Returns the last errstr

(PECL fann >= 1.0.0) Sets the activation steepness for all of the neurons in the supplied layer number

(PECL fann >= 1.0.0) Returns the decay which is a factor that weights should decrease in each iteration during

(PECL fann >= 1.0.0) Returns the initial step-size

(PECL fann >= 1.0.0) The number of activation steepnesses

(PECL fann >= 1.0.0) Sets the maximum out epochs