When to be critical? Performance and evolvability in different regimes of neural Ising agents

It has long been hypothesized that operating close to the critical state is beneficial for natural, artificial and their evolutionary systems. We put this hypothesis to test in a system of evolving foraging agents controlled by neural networks that can adapt agents' dynamical regime throughout...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-11
Hauptverfasser:	Khajehabdollahi, Sina, Prosi, Jan, Giannakakis, Emmanouil, Martius, Georg, Levina, Anna
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Neural and Evolutionary Computing Evolutionary algorithms Fitness Genetic algorithms Ising model Life span Neural networks Perturbation Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!