Austenitic Stainless Steel grade 304L and 316L are very important alloys used in various high temperature applications, which make it important to study their mechanical properties at elevated temperatures. In this work, the mechanical properties such as ultimate tensile strength (UTS), yield strength (Y-S), % elongation, strain hardening exponent (n) and strength coefficient (K) are evaluated based on the experimental data obtained from the uniaxial isothermal tensile tests performed at an interval of 50 degrees C from 50 degrees C to 650 degrees C and at three different strain rates (0.0001, 0.001 and 0.01s(-1)). Artificial Neural Networks (ANN) are trained to predict these mechanical properties. The trained ANN model gives an excellent correlation coefficient and the error values are also significantly low, which represents a good accuracy of the model. The accuracy of the developed ANN model also conforms to the results of mean paired t-test, F-test and Levene's test. (C) 2015 Brazilian Metallurgical, Materials and Mining Association. Published by Elsevier Editora Ltda. All rights reserved.