Applied Evolutionary Algorithms for Engineers using Python

This book is meant for those who seek to apply evolutionary algorithms to problems in engineering and science. To this end, it provides the theoretical background necessary to the understanding of the presented evolutionary algorithms and their shortcomings, while also discussing themes that are pivotal to the successful application of evolutionary algorithms to real-world problems. The theoretical descriptions are illustrated with didactical Python implementations of the algorithms, which not only allow readers to consolidate their understanding, but also provide a sound starting point for those intending to apply evolutionary algorithms to optimization problems in their working fields. Python has been chosen due to its widespread adoption in the Artifical Intelligence community. Those familiar with high level languages such as MATLABTM will not have any difficulty in reading the Python implementations of the evolutionary algorithms provided in the book. Instead of attempting to encompass most of the existing evolutionary algorithms, past and present, the book focuses on those algorithms that researchers have recently applied to difficult optimization problems, such as control problems with continuous action spaces and the training of high-dimensional convolutional neural networks. The basic characteristics of real-world optimization problems are presented, together with advices on how to properly apply evolutionary algorithms to them. The applied nature of the book is reinforced by the presentation of cases of successful application of evolutionary algorithms to optimization problems that are closely related to real-world problems. The presentation is complemented by Python source code, allowing the user to gain insight into the idiosyncrasies of the practical application of evolutionary algorithms. Cover Title Page Copyright Page Preface Contents Glossary Section I: Introduction 1. Evolutionary Algorithms and Difficult Optimization Problems 1.1 What Makes an Optimization Problem Harder to Solve 1.2 Why Evolutionary Algorithms 2. Introduction to Optimization 2.1 What is Optimization 2.2 Solutions of an Optimization Problem 2.3 Maximization or Minimization 2.4 Basic Mathematical Formulation 2.5 Constraints and Feasible Regions 2.6 Local Solutions and Global Solutions 2.7 Multimodality 2.8 Multi-Objective Optimization 2.9 Combinatorial Optimization 3. Introduction to Evolutionary Algorithms 3.1 Representing Candidate Solutions 3.1.1 Discrete Representations 3.1.2 Integer Representation 3.1.3 Real-valued Representation 3.2 Comparing Representations on a Benchmark Problem 3.3 The Fitness Function 3.4 Population 3.5 Selecting Parents 3.5.1 Selection Probabilities 3.5.2 Sampling 3.5.3 Selection of Individuals 3.6 Crossover (Recombination) 3.6.1 Recombination for Discrete Representations 3.6.2 Recombination for Real-valued Representations 3.7 Mutation 3.7.1 Mutation for Binary Representations 3.7.2 Mutation for Real-valued Representations 3.7.3 Mutation for Integer Representations 3.8 Elitism Section II: Single-Objective Evolutionary Algorithms 4. Swarm Optimization 4.1 Ant Colony Optimization 4.2 Particle Swarm Optimization 5. Evolution Strategies 5.1 Recombination Operators 5.2 Mutation Operators 5.3 The (1 + 1) ES 5.4 The (μ + λ) ES 5.5 Natural Evolution Strategies 5.6 Covariance Matrix Adaptation Evolution Strategies 6. Genetic Algorithms 6.1 Real-Valued Genetic Algorithm 6.2 Binary Genetic Algorithm 7. Differential Evolution Section III: Multi-Objective Evolutionary Algorithms 8. Non-Dominated Sorted Genetic Algorithm II 9. Multiobjective Evolutionary Algorithm Based on Decomposition Section IV: Applying Evolutionary Algorithms 10. Solving Optimization Problems with Evolutionary Algorithms 10.1 Benchmark Problems 10.1.1 Single-Objective 10.1.2 Multi-Objective 10.1.3 Noisy 10.2 Dealing with Constraints 10.3 Dealing with Costly Objective Functions 10.4 Dealing with Noise 10.5 Evolutionary Multi-Objective Optimization 10.6 Some Auxiliary Functions 11. Assessing the Performance of Evolutionary Algorithms 11.1 A Cautionary Note 11.2 Performance Metric 11.3 Confidence Intervals 11.4 Assessing the Performance of Single-Objective Evolutionary Algorithms 11.5 Assessing the Performance of Multi-Objective Evolutionary Algorithms 11.6 Benchmark Functions 12. Case Study: Optimal Design of a Gear Train System 13. Case Study: Teaching a Legged Robot How to Walk References Index Applied Evolutionary Algorithms for Engineers with Python is written for students, scientists and engineers who need to apply evolutionary algorithms to practical optimization problems. The presentation of the theoretical background is complemented with didactical Python implementations of evolutionary algorithms that researchers have recently applied to complex optimization problems. Cases of successful application of evolutionary algorithms to real-world like optimization problems are presented, together with source code that allows the reader to gain insight into the idiosyncrasies of the practical application of evolutionary algorithms. Key Features Includes detailed descriptions of evolutionary algorithm paradigms Provides didactic implementations of the algorithms in Python, a programming language that has been widely adopted by the AI community Discusses the application of evolutionary algorithms to real-world optimization problems Presents successful cases of the application of evolutionary algorithms to complex optimization problems, with auxiliary source code. "This book was written for students, scientists and engineers who need to apply evolutionary algorithms to practical optimization problems. The presentation of the theoretical background is complemented with didactical Python implementations of evolutionary algorithms that researchers have recently applied to complex optimization problems. Cases of successful application of evolutionary algorithms to real-world like optimization problems are presented, together with source code that allows the reader to gain insight into the idiosyncrasies of of the practical application of evolutionary algorithms"-- Provided by publisher This book meant for students, scientists and engineers to help in the application of evolutionary algorithms to practical optimization problems. The presentation of theoretical background is complemented with didactical Python implementations of evolutionary algorithms that researchers have recently applied to complex optimization problems. This book is written for students, scientists and engineers who need to apply evolutionary algorithms to practical optimization problems. The presentation of the theoretical background is complemented with didactical Python implementations of evolutionary algorithms that researchers have recently applied to complex optimization problems.