An Improved BP Neural Network and Its Application

The conventional algorithm of the BP neural network has some disadvantages such as in the vicinity of the target, if the learning factor is too small, the convergence may be too slow, and if the learning factor is too large, the convergence may be amended too much, leading to oscillations and even dispersing phenomenon. At the same time, the very slow speed of convergence and the main procedure is easily trapped into local minimum value. To tackle these problems, this paper optimizes the learning factor and the Sigmoid function, and improves the conventional BP neural network. The comparison of the results in the simulation analysis shows that the convergence and the accuracy of the improved algorithm are better than that of the conventional algorithm, and it has some intelligent advantages such as that the accuracy of the evaluation results can be improved by continuous self-learning, and there are not subjective factors interference in the application.