A novel approach using artificial neural networks for representing chemical reactions is developed and successfully implemented with a modeled velocity-scalar joint pdf transport equation for H-2/CO2 turbulent jet diffusion flames. The chemical kinetics are represented using a three-step reduced mechanism, and the transport equation is solved by a Monte Carlo method. A detailed analysis of computational performance and a comparison between the neural network approach and other methods used to represent the chemistry, namely the look-up table, or the direct integration procedures, are presented. A multilayer perceptron architecture is chosen for the neural network. The training algorithm is based on a back-propagation supervised learning procedure with individual momentum terms and adaptive learning rate adjustment for the weights matrix. A new procedure for the selection of training samples using dynamic randomization is developed and is aimed at reducing the possibility of the network being trapped in a local minimum. This algorithm achieved an impressive acceleration in convergence compared with the use of a fixed set of selected training samples. The optimization process of the neural network is discussed in detail. The feasibility of using neural network models to represent highly nonlinear chemical reactions is successfully illustrated. The prediction of the flow field and flame characteristics using the neural network approach is in good agreement with those obtained using other methods, and is also in reasonable agreement with the experimental data. The computational benefits of the neural network approach over the look-up table and the direct integration methods, both in CPU time and RAM storage requirements are not great for a chemical mechanisms of less than three reactions. The neural network approach becomes superior, however, for more complex reaction schemes.