The main aim of this paper is to consider the concept of the basic Back propagation algorithm. The Back propagation algorithm is the principal for training Feed Forward Neural Networks. It is proposed for reduce the mean square error (MSE) between the real outputs of a multilayer feed-forward neural network and the preferred outputs. Back Propagation network has a great advantage of simplicity of implementation and computation compared to other mathematically complicated techniques. This paper concise the basic Back Propagation and continuous upturns over Back propagation technique used for classification in artificial neural networks (ANN) and associate with new methods like genetic algorithms (GA).