Using grid search for parameter tuning

Tuning hyperparameters is a time-consuming and computation-expensive task. Throughout this book, we've paid limited attention to tuning hyperparameters. Most results were obtained with pre-chosen values. To choose the right values, we can use heuristics or an extensive grid search. Grid search is a popular method for parameter tuning in machine learning.

In the following recipe, we will demonstrate how you can apply grid search when building a deep learning model. For this, we will be using Hyperopt. 

How to do it...

1. We start by importing the libraries used in this recipe:

import sys
import numpy as np

from hyperopt import fmin, tpe, hp, STATUS_OK, Trials

from keras.models import...