You're reading from Python Machine Learning by Example Build intelligent systems using Python, TensorFlow 2, PyTorch, and scikit-learn

Product type Paperback

Published in Oct 2020

Publisher Packt

ISBN-13 9781800209718

Length 526 pages

Edition 3rd Edition

Languages

Python

Tools

PyTorch

Concepts

Machine Learning

Author (1):

Yuxi (Hayden) Liu

View More author details

Table of Contents (17) Chapters

Preface

1. Getting Started with Machine Learning and Python

2. Building a Movie Recommendation Engine with Naïve Bayes FREE CHAPTER

3. Recognizing Faces with Support Vector Machine

4. Predicting Online Ad Click-Through with Tree-Based Algorithms

5. Predicting Online Ad Click-Through with Logistic Regression

6. Scaling Up Prediction to Terabyte Click Logs

7. Predicting Stock Prices with Regression Algorithms

8. Predicting Stock Prices with Artificial Neural Networks

9. Mining the 20 Newsgroups Dataset with Text Analysis Techniques

10. Discovering Underlying Topics in the Newsgroups Dataset with Clustering and Topic Modeling

11. Machine Learning Best Practices

12. Categorizing Images of Clothing with Convolutional Neural Networks

13. Making Predictions with Sequences Using Recurrent Neural Networks

14. Making Decisions in Complex Environments with Reinforcement Learning

15. Other Books You May Enjoy

16. Index

Preventing overfitting in neural networks

A neural network is powerful as it can derive hierarchical features from data with the right architecture (the right number of hidden layers and hidden nodes). It offers a great deal of flexibility and can fit a complex dataset. However, this advantage will become a weakness if the network is not given enough control over the learning process. Specifically, it may lead to overfitting if a network is only good at fitting to the training set but is not able to generalize to unseen data. Hence, preventing overfitting is essential to the success of a neural network model.

There are mainly three ways to impose restrictions on our neural networks: L1/L2 regularization, dropout, and early stopping. We practiced the first method in Chapter 5, Predicting Online Ad Click-Through with Logistic Regression, and will discuss another two in this section.