BP（Back Propagation）网络是1986年由Rumelhart和McCelland为首的科学家小组提出，是一种按误差逆传播算法训练的多层前馈网络，是目前应用最广泛的神经网络模型之一。BP网络能学习和存贮大量的输入输出模式映射关系，而无需事前揭示描述这种映射关系的数学方程。它的学习规则是使用最速下降法（梯度法），通过反向传播来不断调整网络的权值和阈值，使网络的误差平方和最小。BP神经网络模型拓扑结构包括输入层（input layer）、隐层(hide layer)和输出层(output layer)。(BP (Back Propagation) network is a group of scientists led by Rumelhart in 1986 and McCelland, is a kind of error back propagation training algorithm for the multilayer feedforward network, the neural network model is one of the most widely used. BP networks can learn and store a large number of mapping relations between input and output patterns without revealing mathematical equations describing such mappings. Its learning rule is to use the steepest descent method (gradient method) to continuously adjust the weights and thresholds of the network by back-propagation, so that the error sum of the network is minimum. BP neural network model topology includes input layer (input, layer), hidden layer (hide, layer) and output layer (output layer).)