Symmetry-Aware Reservoir Computing
Preprint
Abstract
We demonstrate that matching the symmetry properties of a reservoir computer (RC) to the data being processed dramatically increases its processing power. We apply our method to the parity task, a challenging benchmark problem that highlights inversion and permutation symmetries, and to a chaotic system inference task that presents an inversion symmetry rule. For the parity task, our symmetry-aware RC obtains zero error using an exponentially reduced neural network and training data, greatly speeding up the time to result and outperforming hand crafted artificial neural networks. When both symmetries are respected, we find that the network size $N$ necessary to obtain zero error for 50 different RC instances scales linearly with the parity-order $n$. Moreover, some symmetry-aware RC instances perform a zero error classification with only $N=1$ for $n\leq7$. Furthermore, we show that a symmetry-aware RC only needs a training data set with size on the order of $(n+n/2)$ to obtain such performance, an exponential reduction in comparison to a regular RC which requires a training data set with size on the order of $n2^n$ to contain all $2^n$ possible $n-$bit-long sequences. For the inference task, we show that a symmetry-aware RC presents a normalized root-mean-square error three orders-of-magnitude smaller than regular RCs. For both tasks, our RC approach respects the symmetries by adjusting only the input and the output layers, and not by problem-based modifications to the neural network. We anticipate that generalizations of our procedure can be applied in information processing for problems with known symmetries.
Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Next generation reservoir computingNature Communications, 2021
- Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamicsNeural Networks, 2020
- Physical reservoir computing based on spin torque oscillator with forced synchronizationApplied Physics Letters, 2019
- Rapid time series prediction with a hardware-based reservoir computerChaos: An Interdisciplinary Journal of Nonlinear Science, 2018
- Reservoir computing with a single delay-coupled non-linear mechanical oscillatorJournal of Applied Physics, 2018
- Attractor reconstruction by machine learningChaos: An Interdisciplinary Journal of Nonlinear Science, 2018
- Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from dataChaos: An Interdisciplinary Journal of Nonlinear Science, 2017
- Reservoir observers: Model-free inference of unmeasured variables in chaotic systemsChaos: An Interdisciplinary Journal of Nonlinear Science, 2017
- Constructive Neural Network Algorithms That Solve Highly Non-separable Problems2009
- Birthday paradox, coupon collectors, caching algorithms and self-organizing searchDiscrete Applied Mathematics, 1992