The computation of the sensitivity of a Madaline’s output to its parameter perturbation is system- atically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continu- ous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational complexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations. The computation of the sensitivity of a Madaline’s output to its parameter perturbation is system-atically discussed. Firstly, according to the discrete feature of Adalines, a method based on discrete stochastic technique is proposed, which derives some analytical formulas for the computation of Adalines’ sensitivity. The method can theoretically solve some problems that are unsolvable by the existing methods based on continu- ous stochastic techniques, release some unpractical constraints, and make it available to theoretically analyze the approximation error of Adalines’ sensitivity. Secondly, on the basis of the sensitivity of Adalines and the structural characteristics of Madalines, a new selection strategy depending on a type of dedication degree for computing Madalines’ sensitivity is proposed, which is superior to current popular way of simply averaging in both precision and complexity. The proposed formulas and algorithm have the advantages of simplicity, low computational com plexity, small approximation error, and high generality, as have been verified by a great amount of experimental simulations.