Transfer learning of chaotic systems

Can a neural network trained by the time series of system A be used to predict evolution B? This problem, knowing as transfer learning in broad sense, is great importance machine and data mining, yet has not been addressed for chaotic systems. Here we investigate systems from perspective synchronization-based state inference, which reservoir computer infer unmeasured variables B, while different B either parameter or dynamics. It found that if are parameter, can well synchronized B. However, dynamics, fails synchronize with general. Knowledge along chain coupled computers also studied, it that, although systems, driving successfully inferred remote computer. Finally, an experiment pendulum, show knowledge learned modeling experimental system.