在多层前馈神经网络中，前一层的输出信号作为后一层的输入信号，依此类推，

In a multi-layer feedforward neural network, the output signal of the previous layer is used as the input signal of the next layer, and so on, the input signal enters the artificial neural network from the input layer, and is processed by the hidden layer and the function of the output layer, and finally the entire The output signal of the artificial neural network. Generally speaking, adding hidden layers can make the neural network get more efficient statistics, especially for the case of a relatively large amount of input data, the increase in the number of hidden layers can make the neural network's analysis and fitting of the data more accurate.

In a multi-layer feed-forward neural network, the output signal of the former layer acts as the input signal of the latter layer, and so on, the input signal enters the artificial neural network by the input layer, is processed by the function of the hidden layer and the output layer, and finally gets the output signal of the whole artificial neural network. In general, increasing the hidden layer can make the neural network more efficient statistics, especially for the large amount of input data, the increase in the number of hidden layers can make the neural network data analysis and fitting more accurate.

In the multilayer feedforward neural network, the output signal of the former layer is used as the input signal of the latter layer, and so on, the input signal enters the artificial neural network from the input layer, and finally gets the output signal of the whole artificial neural network through the function processing of the hidden layer and the output layer. Generally speaking, adding hidden layer can make neural network get more efficient statistics, especially for the case of large amount of input data, increasing the number of hidden layer can make neural network analysis and fitting of data more accurate.<br>