Consistency is an extension to generalized synchronization which quantifies the degree of functional dependency of a driven nonlinear system to its input. We apply this concept to echo-state networks, which are an artificial-neural network version of reservoir computing. Through a replica test we measure the consistency levels of the high-dimensional response, yielding a comprehensive portrait of the echo-state property.When a nonlinear dynamical system is externally modulated by an information-carrying signal, its erratic response hides an intricate property: Consistency. It is difficult to estimate from time series whether or not the variability in the output is entirely determined by the driving signal. For autonomous chaotic systems it is well-known that their inherent instability gives rise to a certain level of unpredictability. For a driven system, this means that a part of the variability of its output does not depend on the drive. Consistency quantifies the degree of this dependency through a replica test. The nonlinear system is repeatedly driven by the same signal, and the corresponding responses are compared. We apply this concept to echo-state networks, a class of artificial neural networks with a fixed random internal connectivity. Such networks have been successfully utilized for sequential processing tasks like nonlinear time series prediction and spoken digit recognition. Studying the consistency property allows for a more comprehensive understanding of the dynamical response and for tailoring the network systematically towards enhanced functionality and a wider range of applications.

We employ reservoir computing for a reconstruction task in coupled chaotic systems, across a range of dynamical relationships including generalized synchronization. For a drive-response setup, a temporal representation of the synchronized state is discussed as an alternative to the known instantaneous form. The reservoir has access to both representations through its fading memory property, each with advantages in different dynamical regimes. We also extract signatures of the maximal conditional Lyapunov exponent in the performance of variations of the reservoir topology. Moreover, the reservoir model reproduces different levels of consistency where there is no synchronization. In a bidirectional coupling setup, high reconstruction accuracy is achieved despite poor observability and independent of generalized synchronization.

No abstract

We study swarms as dynamical systems for reservoir computing (RC). By example of a modified Reynolds boids model, the specific symmetries and dynamical properties of a swarm are explored with respect to a nonlinear time-series prediction task. Specifically, we seek to extract meaningful information about a predator-like driving signal from the swarm’s response to that signal. We find that the naïve implementation of a swarm for computation is very inefficient, as permutation symmetry of the individual agents reduces the computational capacity. To circumvent this, we distinguish between the computational substrate of the swarm and a separate observation layer, in which the swarm’s response is measured for use in the task. We demonstrate the implementation of a radial basis-localized observation layer for this task. The behavior of the swarm is characterized by order parameters and measures of consistency and related to the performance of the swarm as a reservoir. The relationship between RC performance and swarm behavior demonstrates that optimal computational properties are obtained near a phase transition regime.

To understand the collective motion of many individuals, we often rely on agent-based models with rules that may be computationally complex and involved. For biologically inspired systems in particular, this raises questions about whether the imposed rules are necessarily an accurate reflection of what is being followed. The basic premise of updating one’s state according to some underlying motivation is well suited to the realm of reservoir computing; however, entire swarms of individuals are yet to be tasked with learning movement in this framework. This work focuses on the specific case of many selfish individuals simultaneously optimizing their domains in a manner conducive to reducing their personal risk of predation. Using an echo state network and data generated from the agent-based model, we show that, with an appropriate representation of input and output states, this selfish movement can be learned. This suggests that a more sophisticated neural network, such as a brain, could also learn this behavior and provides an avenue to further the search for realistic movement rules in systems of autonomous individuals.