Time Shifts to Reduce the Size of Reservoir Computers
arXiv:2205.02267 · doi:10.1063/5.0097850
Abstract
A reservoir computer is a type of dynamical system arranged to do computation. Typically, a reservoir computer is constructed by connecting a large number of nonlinear nodes in a network that includes recurrent connections. In order to achieve accurate results, the reservoir usually contains hundreds to thousands of nodes. This high dimensionality makes it difficult to analyze the reservoir computer using tools from dynamical systems theory. Additionally, the need to create and connect large numbers of nonlinear nodes makes it difficult to design and build analog reservoir computers that can be faster and consume less power than digital reservoir computers. We demonstrate here that a reservoir computer may be divided into two parts; a small set of nonlinear nodes (the reservoir), and a separate set of time-shifted reservoir output signals. The time-shifted output signals serve to increase the rank and memory of the reservoir computer, and the set of nonlinear nodes may create an embedding of the input dynamical system. We use this time-shifting technique to obtain excellent performance from an opto-electronic delay-based reservoir computer with only a small number of virtual nodes. Because only a few nonlinear nodes are required, construction of a reservoir computer becomes much easier, and delay-based reservoir computers can operate at much higher speeds.
References in corpus (20)
- Recent Advances in Physical Reservoir Computing: A Review
- Next Generation Reservoir Computing
- Attractor Reconstruction by Machine Learning
- Embedding and Approximation Theorems for Echo State Networks
- Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
- Demonstrating Delay-based Reservoir Computing Using a Compact Photonic Integrated Chip
- Network Structure Effects in Reservoir Computers
- Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
- Do Reservoir Computers Work Best at the Edge of Chaos?
- Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
- Consistency in Echo-State Networks
- PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing
- Chaos on compact manifolds: Differentiable synchronizations beyond the Takens theorem
- Breaking Symmetries of the Reservoir Equations in Echo State Networks
- Optimizing Memory in Reservoir Computers
- Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links
- Fundamental aspects of noise in analog-hardware neural networks
- Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
- Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction
- Reservoir Computers with Random and Optimized Time-Shifts