Handbook of Evolutionary Machine Learning

This book explores how evolution can address machine learning problems and improve current methods, with topics organized into five parts: fundamental concepts, evolutionary computation, neural networks, supporting machine learning methods, and applications in medicine, robotics, science, finance, and other disciplines. It serves as an essential reference for researchers, postgraduate students, practitioners, and those interested in evolutionary approaches to machine learning.

Format: Unspecified
Length: 768 pages
Publication date: 02 November 2023
Publisher: Springer Verlag, Singapore

This comprehensive volume, penned by esteemed international experts in the field of evolutionary approaches to machine learning, delves into a multitude of ways in which evolution can effectively tackle machine learning challenges and enhance existing methodologies. The book is organized into five distinct sections, each covering a different aspect of evolutionary approaches to machine learning.

The first section provides a foundational overview of evolutionary approaches to the three primary classes of learning employed in machine learning: supervised learning, unsupervised learning, and reinforcement learning. It introduces key concepts and highlights the advantages of these approaches.

The second section explores the application of evolutionary computation as a machine learning technique, highlighting methodological advancements in evolutionary clustering, classification, regression, and ensemble learning. It discusses the use of genetic algorithms, simulated annealing, and other optimization techniques to solve complex machine learning problems.

The third section delves into the intricate relationship between evolution and neural networks, particularly focusing on the connections to deep learning, generative and adversarial models, and the remarkable potential of evolution with large language models. It examines how evolutionary processes can be leveraged to improve the performance and adaptability of neural networks.

The fourth section focuses on the practical applications of evolutionary computation in supporting machine learning methods. It discusses methodological developments for evolutionary data preparation, model parametrization, design, and validation. It showcases how evolutionary computation can be used to optimize machine learning models and improve their accuracy and generalization capabilities.

The final section comprises several chapters that explore the wide-ranging applications of evolutionary machine learning in various domains, including medicine, robotics, science, finance, and more. It provides reviews of application areas and showcases real-world examples of evolutionary machine learning solutions to diverse problem domains.

This book serves as an invaluable resource for researchers, postgraduate students, practitioners in industry, and anyone with an interest in evolutionary approaches to machine learning. It provides a comprehensive and up-to-date understanding of the field, covering both theoretical foundations and practical implementations. With its extensive coverage and insightful insights, this book will undoubtedly become a staple in the literature of machine learning and artificial intelligence.

Weight: 1334g
Dimension: 235 x 155 (mm)
ISBN-13: 9789819938131
Edition number: 1st ed. 2024