Reader small image

You're reading from  Neural Network Projects with Python

Product typeBook
Published inFeb 2019
Reading LevelBeginner
PublisherPackt
ISBN-139781789138900
Edition1st Edition
Languages
Right arrow
Author (1)
James Loy
James Loy
author image
James Loy

James Loy has more than five years, expert experience in data science in the finance and healthcare industries. He has worked with the largest bank in Singapore to drive innovation and improve customer loyalty through predictive analytics. He has also experience in the healthcare sector, where he applied data analytics to improve decision-making in hospitals. He has a master's degree in computer science from Georgia Tech, with a specialization in machine learning. His research interest includes deep learning and applied machine learning, as well as developing computer-vision-based AI agents for automation in industry. He writes on Towards Data Science, a popular machine learning website with more than 3 million views per month.
Read more about James Loy

Right arrow

Model building in Keras

We're finally ready to start building our model in Keras. As a reminder, the model architecture that we're going to use is shown in the previous section.

Importing data

First, let's import the dataset. The IMDb movie reviews dataset is already provided in Keras, so we can import it directly:

from keras.datasets import imdb

The imdb class has a load_data main function, which takes in the following important argument:

  • num_words: This is defined as the maximum number of unique words to be loaded. Only the n most common unique words (as they appear in the dataset) will be loaded. If n is small, the training time will be faster at the expense of accuracy. Let's set num_words = 10000...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Neural Network Projects with Python
Published in: Feb 2019Publisher: PacktISBN-13: 9781789138900

Author (1)

author image
James Loy

James Loy has more than five years, expert experience in data science in the finance and healthcare industries. He has worked with the largest bank in Singapore to drive innovation and improve customer loyalty through predictive analytics. He has also experience in the healthcare sector, where he applied data analytics to improve decision-making in hospitals. He has a master's degree in computer science from Georgia Tech, with a specialization in machine learning. His research interest includes deep learning and applied machine learning, as well as developing computer-vision-based AI agents for automation in industry. He writes on Towards Data Science, a popular machine learning website with more than 3 million views per month.
Read more about James Loy