Neutrality: A Necessity for Self-Adaptation
Marc Toussaint, Christian Igel
Abstract
Self-adaptation is used in all main paradigms of evolutionary computation to increase efficiency. We claim that the basis of self-adaptation is the use of neutrality. In the absence of external control neutrality allows a variation of the search distribution without the risk of fitness loss.
Create a lesson
Related papers
Dynamics-preserving network reductions for ride-pooling paths
Karolin Stiller, Nora Molkenthin
Reconstructing the information processing capacity of physical systems from noisy observations
Shun Kotoku, Rodrigo Martínez-Peña, Takatomo Mihana et al.
Spatio-temporal structures in frog chorus with two species examined by laboratory experiments and mathematical modeling
Kanato Kawaguchi, Ryu Takeda, Ikkyu Aihara
Phase-delays shape multistability and basin sizes in Kuramoto networks: analytical estimates from network structure
Kalel L. Rossi, Antonio Mihara, Lyle E. Muller et al.
Arithmetic of the sync basin for pulse-coupled oscillato
K. P. O'Keeffe
Synchronization Pathways and Resilience in Power Grids
Cook Hyun Kim, Jihye Kim, Sangjoon Park et al.