Dropout regularization

Set a probability for each node that will be eliminated to reduce weight reliance on a particular node

With the inverted dropout technique, at test time:

You do not apply dropout (do not randomly eliminate units) and do not keep the 1/keep_prob factor in the calculations used in training

Increasing the parameter keep_prob from (say) 0.5 to 0.6 will likely cause the following:

1. Reducing the regularization effect

2. Causing the neural network to end up with a lower training set error (overfitting)