Exploring the origins of switching dynamics in a multifunctional reservoir computer
This addresses a specific phenomenon in dynamical systems for researchers in reservoir computing, but it appears incremental as it builds on prior studies of metastability.
The paper investigates the origins of switching dynamics in multifunctional reservoir computers when they fail to reconstruct multiple attractors, using the 'seeing double' problem as a paradigmatic setting.
The concept of multifunctionality has enabled reservoir computers (RCs), a type of dynamical system that is typically realised as an artificial neural network, to reconstruct multiple attractors simultaneously using the same set of trained weights. However there are many additional phenomena that arise when training a RC to reconstruct more than one attractor. Previous studies have found that, in certain cases, if the RC fails to reconstruct a coexistence of attractors then it exhibits a form of metastability whereby, without any external input, the state of the RC switches between different modes of behaviour that resemble properties of the attractors it failed to reconstruct. In this paper we explore the origins of these switching dynamics in a paradigmatic setting via the `seeing double' problem.