ann_FF_Jacobian — computes Jacobian by finite differences.
J The Jacobian hypermatrix: each J(:,:,p) have same structure as z(:,p)*x(:,p)', where z(:,p) is the network output given input x(:,p). x Matrix of input patterns, one pattern per column. N Row vector describing the number of neurons per layer. N(1) is the size of input pattern vector, N(size(N,'c')) is the size of output pattern vector (and also target). W The weight hypermatrix. dx The quantity used to perturb each x(i,p) in turn. af The activation function to be used. This parameter is optional, default value "ann_log_activ", i.e. the logistic activation function.