TensorFlow machine learning small case (5)

1. Loss function:
Indicates the difference between the predicted value and the known answer. When the neural network is trained, the loss function is continuously reduced by continuously changing all the parameters of the neural network. Thereby improving the accuracy of the neural network model.
2. Learning rate: To
update parameters, if the learning rate is large, the optimized parameters do not change much, while the learning rate is small, the optimization parameters change greatly, which affects the error.
3. Moving average:
Enhance the generalization ability of the sliding enhanced model.
4. Regularization:
Add weight to each parameter w in the loss function. Introduces model complexity metrics to suppress model noise and reduce overfitting.
5. Overfitting:
The accuracy of the neural network model on the training data set is relatively high, and the accuracy of the new prediction or classification is low, indicating that the generalization ability of the model is poor.