2 papers
nlin.CD2026
Storage and selection of multiple chaotic attractors in minimal reservoir computers
Francesco Martinuzzi, Holger Kantz
Modern predictive modeling increasingly calls for a single learned dynamical substrate to operate across multiple regimes. From a dynamical-systems viewpoint, this capability decom…
nlin.CD2025
Minimal Deterministic Echo State Networks Outperform Random Reservoirs in Learning Chaotic Dynamics
Francesco Martinuzzi
Machine learning (ML) is widely used to model chaotic systems. Among ML approaches, echo state networks (ESNs) have received considerable attention due to their simple construction…