The dynamical regime and its importance for evolvability, task performance and generalization
| Autor: | Emmanouil Giannakakis, Georg Martius, Jan Prosi, Anna Levina, Sina Khajehabdollahi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer science media_common.quotation_subject Closeness Stability (learning theory) Populations and Evolution (q-bio.PE) Computer Science - Neural and Evolutionary Computing Perturbation (astronomy) FOS: Physical sciences Disordered Systems and Neural Networks (cond-mat.dis-nn) Condensed Matter - Disordered Systems and Neural Networks Nonlinear Sciences - Adaptation and Self-Organizing Systems Adaptability Task (project management) Evolvability Criticality FOS: Biological sciences Computer Science - Multiagent Systems Statistical physics Neural and Evolutionary Computing (cs.NE) Quantitative Biology - Populations and Evolution Resilience (network) Adaptation and Self-Organizing Systems (nlin.AO) media_common Multiagent Systems (cs.MA) |
| Zdroj: | Artificial Life Conference Proceedings |
| DOI: | 10.48550/arxiv.2103.12184 |
| Popis: | It has long been hypothesized that operating close to the critical state is beneficial for natural and artificial systems. We test this hypothesis by evolving foraging agents controlled by neural networks that can change the system's dynamical regime throughout evolution. Surprisingly, we find that all populations, regardless of their initial regime, evolve to be subcritical in simple tasks and even strongly subcritical populations can reach comparable performance. We hypothesize that the moderately subcritical regime combines the benefits of generalizability and adaptability brought by closeness to criticality with the stability of the dynamics characteristic for subcritical systems. By a resilience analysis, we find that initially critical agents maintain their fitness level even under environmental changes and degrade slowly with increasing perturbation strength. On the other hand, subcritical agents originally evolved to the same fitness, were often rendered utterly inadequate and degraded faster. We conclude that although the subcritical regime is preferable for a simple task, the optimal deviation from criticality depends on the task difficulty: for harder tasks, agents evolve closer to criticality. Furthermore, subcritical populations cannot find the path to decrease their distance to criticality. In summary, our study suggests that initializing models near criticality is important to find an optimal and flexible solution. Comment: 8 Pages, 7 Figures, Artificial Life Conference 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|