I didn’t play much with hyperparameters, but previous DNN model actually yielded worse accuracy then a logistic regression. We can explore if this is due to overfitting on under-fitting in a separate post.
Tensorflow Tutorial — Part 2
Illia Polosukhin

I see that using metrics such as precision, recall and f1 score separately on training and test set data, we could know if it a overfitting or under-fitting.

Now the question is how do we know about number of units in each hidden layer and number of hidden layers to yield best possible outcome ?

Show your support

Clapping shows how much you appreciated manjush’s story.