Exploring the limits of multifunctionality across different reservoir computers
This work addresses the challenge of multifunctionality in neural networks for researchers in dynamical systems and reservoir computing, but it is incremental as it explores specific parameter effects on known limitations.
The paper investigates the performance limits of multifunctional reservoir computers by training them on tasks involving coexisting chaotic attractors and overlapping circular orbits, finding that reconstruction ability diminishes as data overlaps in state space.
Multifunctional neural networks are capable of performing more than one task without changing any network connections. In this paper we explore the performance of a continuous-time, leaky-integrator, and next-generation `reservoir computer' (RC), when trained on tasks which test the limits of multifunctionality. In the first task we train each RC to reconstruct a coexistence of chaotic attractors from different dynamical systems. By moving the data describing these attractors closer together, we find that the extent to which each RC can reconstruct both attractors diminishes as they begin to overlap in state space. In order to provide a greater understanding of this inhibiting effect, in the second task we train each RC to reconstruct a coexistence of two circular orbits which differ only in the direction of rotation. We examine the critical effects that certain parameters can have in each RC to achieve multifunctionality in this extreme case of completely overlapping training data.