ANN - Toolbox for neural networks
ann_d_log_activ - derivative of logistic activation function 
ann_d_sum_of_sqr - derivative of sum-of-squares error
ANN_FF - To provide engines for feedforward ANN exploration
ann_FF_ConjugGrad - Conjugate Gradient algorithm.
ann_FF_grad - error gradient trough finite differences.
ann_FF_grad_BP - error gradient trough backpropagation
ann_FF_grad_BP_nb - error gradient trough backpropagation (without bias)
ann_FF_grad_nb - error gradient trough finite differences
ann_FF_Hess - computes Hessian by finite differences.
ann_FF_init - initialize the weight hypermatrix.
ann_FF_init_nb - initialize the weight hypermatrix (without bias).
ann_FF_INT - internal implementation of feedforward nets.
ann_FF_Jacobian - computes Jacobian by finite differences.
ann_FF_Jacobian_BP - computes Jacobian trough backpropagation.
ann_FF_Mom_batch - batch backpropagation with momentum.
ann_FF_Mom_batch_nb - batch backpropagation with momentum (without bias).
ann_FF_Mom_online - online backpropagation with momentum.
ann_FF_Mom_online_nb - online backpropagation with momentum.
ann_FF_run - run patterns trough a feedforward net.
ann_FF_run_nb - This function is used to run patterns trough a feedforward network as defined by N and W.
ann_FF_SSAB_batch - Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_SSAB_batch_nb - Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_SSAB_online -  Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_SSAB_online_nb - Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_Std_batch - Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_Std_batch_nb - Returns the updated weight hypermatrix of a feedforward ANN
ann_FF_Std_online - Returns the updated weight hypermatrix of a feedforward ANN, after online training with a given set of patterns.
ann_FF_Std_online_nb - Returns the updated weight hypermatrix of a feedforward ANN, after online training with a given set of patterns.
ann_FF_VHess - This function calculates the product between a vector and Hessian trough a (fast) finite difference procedure.
ANN_GEN - To provide for some functions wich are usefull for a larger number of architectures.
ann_log_activ - This function is the default neuronal activation function.
ann_pat_shuffle - This function randomly shuffles the columns in matrices x and t
ann_sum_of_sqr - This function calculates the sum-of-squares error given y and t.