These contributions, written by the foremost international researchers and practitioners of Genetic Programming (GP), explore the synergy between theoretical and empirical results on real-world problems, producing a comprehensive view of the state of the art in GP.
Topics include: modularity and scalability; evolvability; human-competitive results; the need for important high-impact GP-solvable problems; ; the risks of search stagnation and of cutting off paths to solutions; the need for novelty; empowering GP search with expert knowledge;
In addition, GP symbolic regression is thoroughly discussed, addressing such topics as guaranteed reproducibility of SR; validating SR results, measuring and controlling genotypic complexity; controlling phenotypic complexity; identifying, monitoring, and avoiding over-fitting; finding a comprehensive collection of SR benchmarks, comparing SR to machine learning.
This text is for all GP explorers. Readers will discover large-scale, real-world applications of GP to a variety of problem domains via in-depth presentations of the latest and most significant results.
Inhaltsverzeichnis
What s in an evolved name? The evolution of modularity via tag-based Reference. - Let the Games Evolve! . - Novelty Search and the Problem with Objectives. - A fine-grained view of phenotypes and locality in genetic programming. - Evolution of an Effective Brain-Computer Interface Mouse via Genetic Programming with Adaptive Tarpeian Bloat Control. - Improved Time Series Prediction and Symbolic Regression with Affine Arithmetic. - Computational Complexity Analysis of Genetic Programming Initial Results and Future Directions. - Accuracy in Symbolic Regression. - Human-Computer Interaction in a Computational Evolution System for the Genetic Analysis of Cancer. - Baseline Genetic Programming: Symbolic Regression on Benchmarks for Sensory Evaluation Modeling. - Detecting Shadow Economy Sizes With Symbolic Regression. - The Importance of Being Flat Studying the Program Length Distributions of Operator Equalisation. - FFX: Fast, Scalable, Deterministic Symbolic Regression Technology.
