TensorFlow basis (four) - to build a neural network summary

First, the neural network comprises:

Second, add the optimization function

Third, the full wording (plus regular items, learning rate, moving average):

1.1 before the spread of the network:

1.2 backpropagation network

demo:

generating data generateds.py

Backpropagation network defined before forward.py

backward.py back-propagation network

operation result:

Guess you like

Origin blog.csdn.net/qq_37764129/article/details/94389734