In this work the comparison of the back propagations training algorithms of neural networks, mainly, Resilient back propagation, Conjugate gradient and Levenberg Marquardt methods are narrated. In this paper, material removal rates are predicted by comparing the effectiveness and efficiency of three training algorithms on the networks. Electrical Discharge Machining (EDM), the most non-traditional manufacturing procedures, is popular, due to its not requiring cutting tools and permits machining of hard, brittle, thin and complex geometry. Thus it is very popular in the field of modern manufacturing industries such as surgical components, nuclear industries aerospace. Based on the study and test results, although the Levenberg Marquardt has been found to be faster and having better performance than other algorithms in training, the Resilient back propagation algorithm has the best accuracy in testing period. © 2016, International Journal of Pharmacy and Technology. All rights reserved.