Comparison between Artificial Neural Network Learning Algorithms for Prediction of Student Average considering Effective Factors in Learning and Educational Progress

In this project, by using different learning algorithms in the form of 37 input parameters of network for predicting average considering effective factors in learning and educational progress, the Perceptron artificial neural network have been studied. The requisite data have been obtained through handing out questionnaires between 400 students of Payame Noor University majoring in computer engineering, information technology and computer science. For recognizing the best learning algorithm, 13 common algorithms considering factors such as training time, the percentage of accountability, the index of efficiency ( the mean squared errors), and the number of epoch have been studied after error propagation. Finally the LM algorithm was recognized as the best learning algorithm for prediction of average.