There are two major problems when training neural networks: overfitting and underfitting. Overfitting is a problem that can occur when the model is too sensitive to the training data. The model will then fail to generalize and perform well on new data...
Training a deep neural network can take hours or even days to complete. It is not practical to train such a neural network every time you want to make predictions. In this case, you can save and then later reload your model.