International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 67 - Number 11 |
Year of Publication: 2013 |
Authors: Amrinder Singh Grewal, Vishal Gupta, Rohit Kumar |
10.5120/11441-7028 |
Amrinder Singh Grewal, Vishal Gupta, Rohit Kumar . Comparative Analysis of Neural Network Techniques for Estimation. International Journal of Computer Applications. 67, 11 ( April 2013), 31-34. DOI=10.5120/11441-7028
Software cost estimation is the process of predicting the effort required to develop a software system. Accurate cost estimation helps us complete the project within time and budget. For completing the project in time and budget, one must have efficient estimation technique for predicting project efforts. Artificial neural network is a promising technique to provide efficient and good results when dealing with problems where there are complex relationship between inputs and outputs. Researchers proved better estimation using back propagation techniques like RBP and Bayesian regulation. In this paper further discussion will be about the study and the efficiency of Neural based one step secant back propagation based cost estimation model, Powell-Beale conjugate gradient model and Fletcher-reeves conjugate gradient model. Result is concluded with the best effort predicting model.