How to avoid overfitting on a simple feed forward network

Question

Using the pima indians diabetes dataset I\'m trying to build an accurate model using Keras. I\'ve written the following code:

# Visualize training history
from k         


        

Answer 1

For a dataset like the Diabetes one you can use a much simpler network. Try to reduce the neurons in your second layer. (Is there a specific reason why you chose tanh as the activation there?).

In addition you simply can add an EarlyStopping callback to your training: https://keras.io/callbacks/