论文部分内容阅读
神经网络之非线性计算能力很强,人们日益注重分析立足于神经网络的软件可靠性模型。本文阐述了软件可靠性的基本概念和BP神经网络的基本原理,提出了一种软件可靠性模型的网络结构的设计思路及在此模型上BP算法的训练过程。
Neural networks have strong non-linear computational power, and people pay more attention to the analysis of software reliability based on neural networks. This paper describes the basic concept of software reliability and the basic principle of BP neural network, and presents a design idea of network structure of software reliability model and the training process of BP algorithm in this model.