CDCCLGNESep 4, 2019

Reservoir Computing based on Quenched Chaos

arXiv:1909.01571v121 citations
Originality Incremental advance
AI Analysis

This work addresses a central problem in reservoir computing for improving computational performance, but it appears incremental as it builds on existing chaotic oscillator frameworks with specific enhancements.

The authors tackled the problem of finding reliable reservoirs with large criticality in reservoir computing by proposing a continuous reservoir using transient dynamics of coupled chaotic oscillators in a critical regime with explosive death. This approach showed better results in signal reconstruction tasks compared to existing methods based on explosive synchronization of regular phase oscillators.

Reservoir computing(RC) is a brain-inspired computing framework that employs a transient dynamical system whose reaction to an input signal is transformed to a target output. One of the central problems in RC is to find a reliable reservoir with a large criticality, since computing performance of a reservoir is maximized near the phase transition. In this work, we propose a continuous reservoir that utilizes transient dynamics of coupled chaotic oscillators in a critical regime where sudden amplitude death occurs. This "explosive death" not only brings the system a large criticality which provides a variety of orbits for computing, but also stabilizes them which otherwise diverge soon in chaotic units. The proposed framework shows better results in tasks for signal reconstructions than RC based on explosive synchronization of regular phase oscillators. We also show that the information capacity of the reservoirs can be used as a predictive measure for computational capability of a reservoir at a critical point.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes