关键词：电子信息；软件；可靠性；SMN
摘 要：This chapter presents a single multiplicative neuron model for predicting software failure has been proposed. Standard back propagation and real coded genetic algorithm with mean squarer error as a fitness function are used for optimizing the parameters. The performance of the proposed model is validated using some real software failure data. A comparative study between some existing software reliability models and the proposed model is presented using different comparison criteria.