You're reading from Hands-On Genetic Algorithms with Python Apply genetic algorithms to solve real-world AI and machine learning problems

Product type Paperback

Published in Jul 2024

Publisher Packt

ISBN-13 9781805123798

Length 418 pages

Edition 2nd Edition

Languages

Python

Tools

Jupyter

Concepts

Data Science

Author (1):

Eyal Wirsansky

View More author details

Table of Contents (24) Chapters

Preface

1. Part 1: The Basics of Genetic Algorithms

2. Chapter 1: An Introduction to Genetic Algorithms FREE CHAPTER

3. Chapter 2: Understanding the Key Components of Genetic Algorithms

4. Part 2: Solving Problems with Genetic Algorithms

5. Chapter 3: Using the DEAP Framework

6. Chapter 4: Combinatorial Optimization

7. Chapter 5: Constraint Satisfaction

8. Chapter 6: Optimizing Continuous Functions

9. Part 3: Artificial Intelligence Applications of Genetic Algorithms

10. Chapter 7: Enhancing Machine Learning Models Using Feature Selection

11. Chapter 8: Hyperparameter Tuning of Machine Learning Models

12. Chapter 9: Architecture Optimization of Deep Learning Networks

13. Chapter 10: Reinforcement Learning with Genetic Algorithms

14. Chapter 11: Natural Language Processing

15. Chapter 12: Explainable AI, Causality, and Counterfactuals with Genetic Algorithms

16. Part 4: Enhancing Performance with Concurrency and Cloud Strategies

17. Chapter 13: Accelerating Genetic Algorithms – the Power of Concurrency

18. Chapter 14: Beyond Local Resources – Scaling Genetic Algorithms in the Cloud

19. Part 5: Related Technologies

20. Chapter 15: Evolutionary Image Reconstruction with Genetic Algorithms

21. Chapter 16: Other Evolutionary and Bio-Inspired Computation Techniques

22. Index

Why subscribe?

23. Other Books You May Enjoy

Real-coded genetic algorithms

So far, we have seen chromosomes that represent binary or integer parameters. Consequently, the genetic operators were suitable for working on these types of chromosomes. However, we often encounter problems where the solution space is continuous. In other words, the individuals are made up of real (floating-point) numbers.

Historically, genetic algorithms used binary strings to represent integers as well as real numbers; however, this was not ideal. The precision of a real number represented using a binary string is limited by the length of the string (number of bits). Since we need to determine this length in advance, we may end up with binary strings that are too short, resulting in insufficient precision, or are overly long.

Moreover, when a binary string is used to represent a number, the significance of each bit varies by its location – the most significant bit being on the left. This can cause imbalance related to schemas – the...