Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Physical Reservoir Computing Enabled by Solitary Waves and Biologically-Inspired Nonlinear Transformation of Input Data

Ivan S. Maksymov

TL;DR

This work addresses the need for energy-efficient, hardware-friendly reservoir computing by substituting random reservoirs with a biologically-inspired nonlinear input transformation realized through solitary-like waves on a flowing liquid film. The authors build a low-cost Arduino-based prototype that uses SL waves to encode input data as a nonlinear functional, enabling generative-mode RC without explicit feedback. The approach forecasts Mackey–Glass time series with shorter training and demonstrates competitive, if not superior, performance compared to traditional RC on a high-performance computer, while consuming far less power and cost. This fluid-based neuromorphic platform points toward bio-inspired, energy-efficient hardware variants of reservoir computing and potential bio-fluidic neural interfaces.

Abstract

Reservoir computing (RC) systems can efficiently forecast chaotic time series using nonlinear dynamical properties of an artificial neural network of random connections. The versatility of RC systems has motivated further research on both hardware counterparts of traditional RC algorithms and more efficient RC-like schemes. Inspired by the nonlinear processes in a living biological brain and using solitary waves excited on the surface of a flowing liquid film, in this paper we experimentally validate a physical RC system that substitutes the effect of randomness for a nonlinear transformation of input data. Carrying out all operations using a microcontroller with a minimal computational power, we demonstrate that the so-designed RC system serves as a technically simple hardware counterpart to the `next-generation' improvement of the traditional RC algorithm.

Physical Reservoir Computing Enabled by Solitary Waves and Biologically-Inspired Nonlinear Transformation of Input Data

TL;DR

This work addresses the need for energy-efficient, hardware-friendly reservoir computing by substituting random reservoirs with a biologically-inspired nonlinear input transformation realized through solitary-like waves on a flowing liquid film. The authors build a low-cost Arduino-based prototype that uses SL waves to encode input data as a nonlinear functional, enabling generative-mode RC without explicit feedback. The approach forecasts Mackey–Glass time series with shorter training and demonstrates competitive, if not superior, performance compared to traditional RC on a high-performance computer, while consuming far less power and cost. This fluid-based neuromorphic platform points toward bio-inspired, energy-efficient hardware variants of reservoir computing and potential bio-fluidic neural interfaces.

Abstract

Reservoir computing (RC) systems can efficiently forecast chaotic time series using nonlinear dynamical properties of an artificial neural network of random connections. The versatility of RC systems has motivated further research on both hardware counterparts of traditional RC algorithms and more efficient RC-like schemes. Inspired by the nonlinear processes in a living biological brain and using solitary waves excited on the surface of a flowing liquid film, in this paper we experimentally validate a physical RC system that substitutes the effect of randomness for a nonlinear transformation of input data. Carrying out all operations using a microcontroller with a minimal computational power, we demonstrate that the so-designed RC system serves as a technically simple hardware counterpart to the `next-generation' improvement of the traditional RC algorithm.
Paper Structure (14 sections, 1 equation, 5 figures)

This paper contains 14 sections, 1 equation, 5 figures.

Table of Contents

  1. Introduction
  2. State-of-the-art
  3. Traditional Reservoir Computing Algorithm
  4. Next Generation Algorithmic Reservoir Computing
  5. Physical Reservoir Computing Systems Based on Solitary Waves
  6. Experimental Setup
  7. Results
  8. Formation of the Nonlinear Functional
  9. Advantages for Generative Mode Operation
  10. Free-running Forecast of Chaotic Time Series
  11. Discussion
  12. Energy Efficiency, Power Consumption and Cost
  13. Potential Applications
  14. Conclusions

Figures (5)

  • Figure S1: Schematic representation of (a) a traditional algorithmic RC system and (b) an RC system with a reservoir of random connection substituted by a nonlinear functional of the input data.
  • Figure S2: (a) Sketch and (b) top view fluorescence photograph of the experimental setup used to validate the proposed architecture of the physical RC system. The fluorescent dye, UV light and digital camera play an auxiliary role and can be removed from the setup without compromising its operation. The remaining components of the setup are controlled by an Arduino microcontroller that is also used to process the raw data traces.
  • Figure S3: (a) Input sinusoidal signal (the dotted curve) and the SL waves excited by it (the solid curve). (b) Fourier spectra of the signals in Panel (a). (c) Free-running forecast of the future evolution of the sinusoidal waves made by the RC system based on the SL waves. Note that the timescale in Panel (c) is unrelated to that in Panel (a).
  • Figure S4: Input MGTS signal (the dotted curve) and the SL waves excited by it (the solid curve). Unlike in Figure \ref{['Fig3']}a, since each variation of MGTS results in the generation of SL waves with different amplitude and propagation speed, the SL waves collide and form more complex wave profiles.
  • Figure S5: Generative mode operation (free-running forecast) of (a) physical RC system based on SL waves and (b) traditional algorithmic RC system (the solid curve) compared with the target MGTS (the dotted curve). (c) Modulus of absolute error of the forecasts produced by the physical and traditional RC algorithmic systems. Note that for the sake of comparison the error of the traditional RC system is plotted with the negative sign.