Evolutionary and genetic algorithms have been around for several decades. Computationally, evolutionary methods for machine learning are not nearly as powerful as deep learning. However, evolutionary methods can provide us with unique tools to assist in a wide variety of optimization patterns, from hyperparameter tuning to network architectures. But before we discuss these patterns, we need to introduce evolutionary and genetic algorithms.
In chapter 1, we introduce the concept of using evolutionary methods for optimizing deep learning systems. Since the deep learning optimization methods we cover in this book fall under automated machine learning, we also introduce AutoML with evolution.
Chapter 2 then introduces life simulation from Conway’s Game of Life, using a simple scenario that is later evolved with genetic algorithms. From there, chapter 3 introduces genetic algorithms in various forms, using distributed genetic algorithms in Python (DEAP). Finally, in chapter 4, we round out the section of chapters by introducing other diverse forms of evolutionary methods.