BP神经网络FORTRAN源代码。

BP算法由两部分组成：信息的正向传递与误差的反向传播。在正向传播过程中，输入信息从输入经隐含层逐层计算传向输出层，每一层神经元的状态只影响下一层神经元的状态。如果在输出层没有得到期望的输出，则计算输出层的误差变化值，然后转向反向传播，通过网络将误差信号沿原来的连接通路反传过来修改各层神经元的权值直至达到期望目标。

-BP neural network FORTRAN source code. BP algorithm consists of two parts: information transmission and forward error back-propagation. In the forward propagation, the input information from the input layer by layer through the hidden layer the calculation transmitted to the output layer, each layer of neurons under the influence of the state is only a layer of neurons in the state. If the output layer has not been the expected output, then the calculation of changes in the value of the output layer error, and then turned back propagation through the network connection error signal along the original path-propagation over the right to modify the value of each layer of neurons until they reach the desired target .