Risk Evaluation Of Software Project Based On An Algorithm Of Parallelism Back-Propagation Neural Networks

Back Propagation neural network was widely used in prediction,identification, automatic control, diagnosis, classification, nonlinear approximation and other fields,At present, Although It is the most widely used in the algorithm of artificial neural network,but the defects can not be ignored,such as converging slowly and falling in a false local minimum.These defects affect the further promotion and the application of BP algorithm.Software project can be considered as a huge systematic engineering,Even though most of software projects make careful plans and proper controls, it is also quite difficult to ensure the desired objectives of the projects. Therefore the risks of software project earn widespread respect in project practice, and risk management goes to be the key to software project management. To a great degree the success of risk management means the success of software project. Assessment which is one part of risk management plays a crucial role.Based on the above issues,In the thesis,Firstly,propose a strategy of BP parallelizati-on,it not only increased the overall training speed, but also improved the training accura-cy. Secondly,establish a scientific and feasible risk evaluation model of software projects, this model not only improved the success rate of software projects development,but also, ensured the quality of software projects.Last, design a risk evaluation model of software project based on algorithm of parallelism BP, verify the effectiveness of training model by C language program,it is of great practical significance.