Limiting ourselves to nets with no hidden nodes , but possibly having more than one output node , let p be an element in a training set , and t be the corresponding target of output node n 将我们的网络限制为没有隐藏节点，但是可能会有不止一个的输出节点，设p是一组培训中的一个元素， t ( p , n )是相应的输出节点n的目标。
When output nodes take their inputs from hidden nodes , and the net finds that it is in error , its weight adjustments require an algorithm that will pick out how much the various nodes contributed to its overall error . the net needs to ask , " who led me astray 当输出节点从隐藏节点获得输入，网络发现出现了误差，权系数的调整需要一个算法来找出整个误差是由多少不同的节点造成的，网络需要问， “是谁让我误入歧途？
We deduce frondose algorithm of three layers bp neural networks which is used in common , and discuss several important issues in designing neural networks which is used to forecast , for example , number of hidden layer , nerve cell number of hidden layer , epoch of learning , embryonic power value , decision of node number about input and outputo at the same time , this dissertation sums up things that conventional bp algorithm is improved on considering disadvantages of it 3推导了常用的三层bp神经网络具体算法，讨论了实际预测应用中神经网络设计方面的几个重要问题，如隐层数、隐层神经元数、训练次数、初始权值、输入节点数以及输出节点数的确定。同时，针对传统bp算法存在的各种各样的缺点，文中综述了对其改进的情况。
Abstract : the calculation of the minimum route set for network system from input node to output node using the join matrix method was discussed . a computer algorithm for this calculation and a pad were presented . the algorithm is valuable in network system reliability analysis 摘要：讨论了用联络矩阵法求网络系统从输入节点到输出节点的所有最小路集，给出了一种实现此方法的计算机算法，画出了实现此算法的pad图，此算法在网络系统可靠性分析方面具有很好的应用价值。
