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，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）、隐层(hide layer)和输出层(output layer)。-BP (Back Propagation) network is proposed in 1986, a team of scientists led by Rumelhart and McCelland, is one kind according to the error back-propagation algorithm for training multilayer feedforward network, is one of the most widely used at present neural network model. BP network can learn and store a lot of input- output model mapping, without prior to reveal the mathematical equations describing the mapping relation. Its learning rule is to use the steepest descent method, through the back-propagation network to continuously adjust the weights and thresholds of the network, the error square and minimum. BP neural network topology, including input layer, hidden layer (input) (hide layer) and the output layer (output layer).