There are two ways to learn a neural network. During the training process, input samples and output samples are provided to the network and unsupervised learning adapts to the input space. Learning rule of neural network is a weight correction algorithm. The learning process of BP neural network can be divided into two stages: the forward propagation process of information and the backward propagation process of the error. BP algorithm is a reverse propagation algorithm. If the external input signal is unable to obtain the desired output via the hidden layer of the neuron layer and the input layer, the external input signal enters the error back propagation process and returns the error between the actual value and the network output value along the original connection path. By changing the weight of the connection of each layer of the neurons, the error decreases and then the forward propagation process is repeated and repeated until the error is less than a given value.<br>
正在翻译中..