You're reading from Machine Learning for Imbalanced Data Tackle imbalanced datasets using machine learning and deep learning techniques

Product type Paperback

Published in Nov 2023

Publisher Packt

ISBN-13 9781801070836

Length 344 pages

Edition 1st Edition

Languages

Rust

Tools

TensorFlow Lite

Concepts

Data Science

Authors (2):

Dr. Mounir Abdelaziz

Kumar Abhishek

View More author details

Table of Contents (15) Chapters

Preface

1. Chapter 1: Introduction to Data Imbalance in Machine Learning FREE CHAPTER

2. Chapter 2: Oversampling Methods

3. Chapter 3: Undersampling Methods

4. Chapter 4: Ensemble Methods

5. Chapter 5: Cost-Sensitive Learning

6. Chapter 6: Data Imbalance in Deep Learning

7. Chapter 7: Data-Level Deep Learning Methods

8. Chapter 8: Algorithm-Level Deep Learning Techniques

9. Chapter 9: Hybrid Deep Learning Methods

10. Chapter 10: Model Calibration

11. Assessments

12. Index

Why subscribe?

13. Other Books You May Enjoy

Appendix: Machine Learning Pipeline in Production

To get the most out of this book

This book assumes some foundational knowledge of ML, deep learning, and Python programming. Some basic working knowledge of scikit-learn and PyTorch can be helpful, although they can be learned on the go.

Software/hardware covered in the book	Operating system requirements
Google Colab	Windows, macOS, or Linux

For the software requirements, you have two options to execute the code provided in this book. You can choose to either run the code within Google Colab online at https://colab.research.google.com/ or download the code to your local computer and execute it there. Google Colab provides a hassle-free option as it comes with all the necessary libraries pre-installed, so you don’t need to install anything on your local machine. All you need is a web browser to access Google Colab and a Google account. If you prefer to work locally, ensure that you have Python (3.6 or higher) installed, as well as the specified libraries such as PyTorch, torchvision, NumPy, and scikit-learn. A list of required libraries can be found in the GitHub repository of the book. These libraries are compatible with Windows, macOS, and Linux operating systems. A modern GPU can speed up the code execution for the deep learning chapters that appear later in the book; however, it’s not mandatory.

If you are using the digital version of this book, we advise you to type the code yourself or access the code from the book’s GitHub repository (a link is available in the next section). Doing so will help you avoid any potential errors related to the copying and pasting of code.

Regarding references, we use numbered references such as “[6],” where you can go to the References section at the end of that chapter and download the corresponding reference (paper/blog/article) either using the link (if mentioned) or searching for that reference on Google Scholar (https://scholar.google.com/).

At the conclusion of each chapter, you will find a set of questions designed to test your comprehension of the material covered. We strongly encourage you to engage with these questions to reinforce your learning. Solutions or answers to selected questions can be found in Assessments towards the end of this book.