What is BP neural network?

The basic idea of ​​the BP algorithm is: the learning process consists of two parts: forward propagation of the signal and reverse propagation of the error; during forward propagation, the input sample is passed in from the input layer and passes through each hidden layer. It is processed layer by layer in turn and transmitted to the output layer. If the output of the output layer does not match the expectation, the error will be transmitted back layer by layer as an adjustment signal, and the connection weight matrix between neurons will be processed to reduce the error. After repeated learning, the error is finally reduced to an acceptable range. The specific steps are as follows:

1. Take a certain sample from the training set and input the information into the network.

2. After forward processing layer by layer through the connection between each node, the actual output of the neural network is obtained.

3. Calculate the error between the actual output of the network and the expected output.

4. Reversely propagate the error back to the previous layers layer by layer, and load the error signal onto the connection weight according to certain principles, so that the connection weight of the entire neural network moves in the direction of error reduction. Transformation.

5. Repeat the above steps for each input-output sample pair in the training set until the error of the entire training sample set is reduced to meet the requirements.