Hyperparameter optimization chapter

[mehradans92]

This chapter discusses techniques for hyperparameter optimization in deep learning:

• [x] Discussion on training hyperparameters (learning rate, number of hidden layers, number of nodes, dropout rate, batch size and number of epochs to train, regularization, dropout)

• [x] Discussion on hyperparameter optimization techniques (search algorithms and trial schedulers, Bayesian optimization)

• [x] Include an example for hyperparameter tuning on an existing example in the book.

[mehradans92]

@whitead which existing example sounds good to you for the third task?

[whitead]

@mehradans92 maybe std layer chapter - which had some discussion of hyperparameter choices

[whitead]

@mehradans92 I think you missed some conflicts. Check the bib file for =======.