A neural network procedure is applied to solve an ill-posed inverse problem in chemical kinetics relevant to chemical and biological areas; calculation of rate constants for the jack-bean urease denaturation by an anionic surfactant agent from experimental enzyme concentrations. The efficiency of the algorithm proposed is compared with the Simplex and the Levenberg Marquardt techniques, often used in nonlinear regression methods to solve this kind of kineticsproblem. The neural network approach is numerically stable and robust with respect to different initial guesses for the C 2012 Wileyrate constants and noises in experimental data. V Periodicals, Inc.