ABSTRACT Artificial neural network (ANN) is an input–output modeling technique that has been successfully implemented in the field of material science to predict material behavior in terms of constitutive models. The material behavior considered here is the stress–strain behavior of the material at elevated temperatures that is characterized by a single-peak flow curve consisting of characteristic points viz. critical stress, peak stress and steady-state stress. The present work focuses on predicting these stress values along with the corresponding strain values through statistical regression analysis (SRA), ANN, and multi-layer complex neural network (MLCNN) with reasonable accuracy. The flow curves obtained from the axisymmetric compression test of 304LN austenitic stainless steel, performed at constant temperatures and constant strain rates, are used to train the models. The MLCNN has performed best while SRA has performed relatively worst with the current dataset due to rigorous and thorough computation. Both MLCNN and ANN are observed to perform better than SRA because of their non-parametric nature of handling data.