Cartesian Genetic Programming

Cartesian Genetic Programming (CGP) is an evolutionary algorithm used to automatically design and optimize complex systems, particularly neural networks and other computational models. Current research focuses on addressing limitations like positional bias through novel genotype reordering strategies and exploring CGP's application in neural architecture search (NAS), symbolic regression, and the evolution of learning rules for spiking neural networks. This approach offers a powerful alternative to manual design, enabling the creation of more efficient and interpretable models across diverse fields, from biomedical image analysis to space applications.