Seeing double with a multifunctional reservoir computer
This work addresses the challenge of multifunctionality in machine learning systems, which is incremental as it builds on existing reservoir computing and multistability concepts.
The paper tackled the problem of enabling artificial neural networks to perform multiple tasks without changing network properties by exploring how the relationship between different attractors affects a reservoir computer's ability to achieve multifunctionality, discovering that multifunctionality critically depends on the spectral radius as overlap increases.
Multifunctional biological neural networks exploit multistability in order to perform multiple tasks without changing any network properties. Enabling artificial neural networks (ANNs) to obtain certain multistabilities in order to perform several tasks, where each task is related to a particular attractor in the network's state space, naturally has many benefits from a machine learning perspective. Given the association to multistability, in this paper we explore how the relationship between different attractors influences the ability of a reservoir computer (RC), which is a dynamical system in the form of an ANN, to achieve multifunctionality. We construct the `seeing double' problem to systematically study how a RC reconstructs a coexistence of attractors when there is an overlap between them. As the amount of overlap increases, we discover that for multifunctionality to occur, there is a critical dependence on a suitable choice of the spectral radius for the RC's internal network connections. A bifurcation analysis reveals how multifunctionality emerges and is destroyed as the RC enters a chaotic regime that can lead to chaotic itinerancy.