Linear Genetic Programming (LGP) represents a significant branch of evolutionary computation that continues to advance both in theoretical understanding and practical applications. This comprehensive volume provides researchers, practitioners, and students with an up-to-date examination of LGP, covering developments since the field's first dedicated book appeared in 2007. As machine learning and artificial intelligence increasingly drive innovation across application fields, LGP's ability to evolve computer programs in a linear sequence of instructions has proven particularly valuable for complex real-world problems.
This edited collection brings together leading experts to explore theoretical advances, novel applications, and modern implementation strategies in LGP. The book covers crucial developments in areas such as convergence behavior, genotype-phenotype mapping, and operator effectiveness, while showcasing LGP's practical impact through applications in control systems, environmental modeling, mathematical discovery, and automated machine learning (AutoML). Special attention is given to modern implementation approaches, including GPU acceleration, field-programmable gate array (FPGA) deployment, and software engineering best practices that enable efficient LGP system development.
Readers will gain a thorough understanding of both fundamental concepts and cutting-edge developments in the field, enabling them to implement and extend LGP systems for their own applications. While primarily intended for researchers and practitioners in evolutionary computation and machine learning, the book assumes only basic knowledge of genetic programming and computer science. Each chapter builds progressively on core concepts, making the material accessible while maintaining technical depth and rigor.
Table of Contents:
Chapter 1 Introduction.- Chapter 2 Fundamentals of Linear Genetic Programming.- Chapter 3 A Theoretical Study On Fitness Supremum in Linear Genetic Programming.- Chapter 4 Long Term Evolution Experiments with Linear Genetic Programming.- Chapter 5 TinyLGP: A Minimalist Implementation of Linear Genetic Programming.- Chapter 6 Linear Genetic Programming with Push.- Chapter 7 An FPGA-Based Architecture for Accelerating Linear Genetic Programming Evaluation.- Chapter 8 Small Nimble LGP Populations for Shifting Streaming Classification Tasks.- Chapter 9 Path-Local Learning in Reward-Modulated Tangled Program Graphs.- Chapter 10 Evolution of Heuristics using Large Language Models.- Chapter 11 Summary and Conclusion.
About the Author :
Wolfgang Banzhaf is the John R. Koza Chair for Genetic Programming, the first endowed chair dedicated to Evolutionary Computation in the United States, and a professor in the Department of Computer Science and Engineering at Michigan State University, East Lansing, USA. His research interests are in the field of bio-inspired computing, notably evolutionary computation and complex adaptive system, and in particular genetic programming and artificial life. He is the (co-)author of more than 300 scientific contributions and 7 patents. His books and edited volumes include “Genetic Programming – An Introduction” (1998), “Linear Genetic Programming” (2007), “Artificial Chemistries” (2015) and most recently, the “Handbook of Evolutionary Machine Learning” (2024).
Ting Hu is an Associate Professor at the School of Computing, Queen’s University in Kingston, Ontario, Canada. Her research focuses on evolutionary computing, explainable AI, and machine learning applications in biomedicine. Ting has published more than 100 scientific contributions. She serves as Special Communications Editor of the Springer journal Genetic Programming and Evolvable Machines, as well as an Associate Editor of the journal BMC BioData Mining.
