Skip to Content
Neural Network Projects with Python
book

Neural Network Projects with Python

by James Loy
February 2019
Beginner to intermediate
308 pages
7h 42m
English
Packt Publishing
Content preview from Neural Network Projects with Python

Splitting the data into training, testing, and validation sets

The last step in data preprocessing is to split the data into training, testing, and validation sets:

  • Training set: The neural network will be trained on this subset of the data.
  • Validation set: This set of data allows us to perform hyperparameter tuning (that is, tuning the number of hidden layers) using an unbiased source of data.
  • Testing set: The final evaluation of the neural network will be based on this subset of the data.

The purpose of splitting the data into training, testing, and validation sets is to avoid overfitting and to provide an unbiased source of data for evaluating model performance. Typically, we will use the training and validation set to tune and improve ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Machine Learning with Python Cookbook

Machine Learning with Python Cookbook

Chris Albon

Publisher Resources

ISBN: 9781789138900Supplemental Content