In the recent years, the metallurgy of high manganese steels especially twinning induced plasticity steels (TWIP) and Transformation induced plasticity (TRIP) has been considered as an important scientific issue. The excellent combinations of Due to the appropriate chemical structure, these steels possess desirable strength and ductility. High Mn austenitic TWIP steels provide a great potential in industrial applications especially for structural components in the automobile industry owing to their excellent combination of strength and ductility. It has been reported that such combination is attributed to austenite matrix as well as twinning process during plastic deformation In recent years artificial neural network has been widely used to predict properties of materials without using expensive and time-consuming trial and methods. Therefore, in this study artificial intelligence was employed to study and predict the mechanical properties of TWIP / TRIP steels. Input variables for the neural network were chemical composition parameters (weight percent of manganese, aluminum and silicon) and thermomechanical parameters (such as annealing temperature, annealing time and the percentage of cold work). the neural network was designed and trained in such a way that could predict the effect of above mentioned parameters on output and favored variables such as yield strength, tensile strength and percentage elongation. Feeding data for the network was extracted from the credential sources and papers. Among the data, 20% was assigned for test stage, 20% for verification, and the remaining 60% was used for training the network. Neural network program was developed separately for each categories of chemical and mechanical parameters. Three separate programs were designed to achieve more accurate results for each group of parameters. Also two methods, i.e. back-propagation error and radial basis were utilized during the neural network. By using the neural networks, influence of each parameter on the mechanical properties were investigated, and the weught percent of each impact was determined. The results indicated that the trained model could precisely predict the sensitivity of the mechanical properties corresponding to the input variables. In the next step, using the results of neural networks, genetic algorithms equations for the model were estimated, by which the results obtained from the neural network were optimized. Keywords: high manganese steels, TRIP, TWIP, mechanical properties, chemical parameters, thermomechanical parameters, neural network, genetic algorithm