Tensorflow overfitting, validation set and improving performance #Neural_Netowkrs #AI #Deep_learning

In this video I’m going to show you how to use a validation set, detect / stop overfitting, and get the best performance out of your data by reducing the learning rate. We are going to achieve this by using early stopping and reduced learning on a plateau.

Code:
colab.research.google.com/drive/1g-cLrL_gE1uQN3yHv…

Sources:
github.com/Jaewan-Yun/optimizer-visualization
keras.io/api/callbacks/early_stopping/
keras.io/api/callbacks/reduce_lr_on_plateau/