Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Physical Reservoir Computing Enabled by Solitary Waves and Biologically-Inspired Nonlinear Transformation of Input Data (2402.03319v1)

Published 3 Jan 2024 in cs.NE, cs.AI, nlin.CD, nlin.PS, and physics.flu-dyn

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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (108)
  1. Babloyantz, A. Chaotic Dynamics in Brain Activity. In Proceedings of the Dynamics of Sensory and Cognitive Processing by the Brain; Başar, E., Ed.; Springer Berlin Heidelberg: Berlin, Heidelberg, 1988; pp. 196–202.
  2. The brain as a dynamic physical system. Neuroscience 1994, 60, 587–605.
  3. Is there chaos in the brain? II. Experimental evidence and related models. C. R. Biol. 2003, 326, 787–840.
  4. Muratov, C.B. A quantitative approximation scheme for the traveling wave solutions in the Hodgkin-Huxley model. Biophys. J. 2000, 79, 2893–2901.
  5. On soliton propagation in biomembranes and nerves. PNAS 2005, 102, 9790–9795.
  6. Penetration of action potentials during collision in the median and lateral giant axons of invertebrate. Phys. Rev. X 2014, 4, 031047.
  7. Catastrophe and hysteresis by the emerging of soliton-like solutions in a nerve model. J. Nonlinear Dyn. 2014, 2014, 710152.
  8. Mechanical surface waves accompany action potential propagation. Nat. Commun. 2015, 6, 6697.
  9. Electromechanical coupling of waves in nerve fibres. Biomech. Model. Mechanobiol. 2018, 17, 1771–1783.
  10. Linear and nonlinear pathways of spectral information transmission in the cochlear nucleus. PNAS 2000, 97, 11780–11786.
  11. Nonlinear spectrotemporal sound analysis by neurons in the auditory midbrain. J. Neurosci. 2002, 22, 4114–4131.
  12. Levitin, D.J. This is Your Brain on Music: The Science of Human Obsession; Dutton, 2006.
  13. Nonlinear auditory models yield new insights into representations of vowels. Atten. Percept. Psychophys. 2019, 81, 1034–1046.
  14. Estimating and interpreting nonlinear receptive field of sensory neural responses with deep neural network models. eLife 2020, 9, e53445. https://doi.org/10.7554/eLife.53445.
  15. Neural correlates of the pitch of complex tones. I. Pitch and pitch salience. J. Neurophysiol. 1996, 76, 1698–1716.
  16. Janata, P. Electrophysiological studies of auditory contexts; PhD Thesis, The University of Oregon, 1996.
  17. Chialvo, D.R. How we hear what is not there: A neural mechanism for the missing fundamental illusion. Chaos 2003, 13, 1226–1230.
  18. Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 2002, 14, 2531–2560.
  19. Adamatzky, A. Advances in Unconventional Computing. Volume 2: Prototypes, Models and Algorithms; Springer, Berlin, 2017.
  20. Polynomial activation neural networks: Modeling, stability analysis and coverage BP-training. Neurocomputing 2019, 359, 227–240.
  21. Physics for neuromorphic computing. Nat. Rev. Phys. 2020, 2, 499–510.
  22. Neuro-inspired computing chips. Nat. Electron. 2020, 3, 371–382.
  23. A bioinspired analogous nerve towards artificial intelligence. Nat. Commun. 2020, 11, 268.
  24. Liquid time-constant networks. Proc. 35th AAAI Conference on Artificial Intelligence (AAAI-21) 2021, pp. 7657–7666.
  25. Nonlinear system identification of neural systems from neurophysiological signals. Neurosci. 2021, 458, 213–228.
  26. Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware. Nat. Commun. 2022, 13, 7847.
  27. Task-adaptive physical reservoir computing. Nat. Mater. 2023. https://doi.org/https://doi.org/10.1038/s41563-023-01698-8.
  28. Self-learning machines based on Hamiltonian echo backpropagation. Phys. Rev. X 2023, 13, 031020.
  29. Brain-inspired organic electronics: Merging neuromorphic computing and bioelectronics using conductive polymers. Adv. Funct. Mater., p. 2307729. https://doi.org/https://doi.org/10.1002/adfm.202307729.
  30. Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 2009, 3, 127–149.
  31. Reservoir Computing; Springer, Berlin, 2021.
  32. Hands-on reservoir computing: a tutorial for practical implementation. Neuromorph. Comput. Eng. 2022, 2, 032002.
  33. Next generation reservoir computing. Nat. Commun. 2021, 12, 5564.
  34. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 2004, 304, 78–80.
  35. Kirby, K.G. Context dynamics in neural sequential learning. Proc. Florida AI Research Symposium (FLAIRS) 1991, pp. 66–70.
  36. Jaeger, H. Echo state network. Scholarpedia 2007, 2, 2330. revision #196567, https://doi.org/10.4249/scholarpedia.2330.
  37. Maksymov, I.S. Analogue and physical reservoir computing using water waves: Applications in power engineering and beyond. Energies 2023, 16, 5366.
  38. Lukoševičius, M. A Practical Guide to Applying Echo State Networks. In Neural Networks: Tricks of the Trade, Reloaded; Montavon, G.; Orr, G.B.; Müller, K.R., Eds.; Springer: Berlin, 2012; pp. 659–686.
  39. Quantum reservoir computing implementation on coherently coupled quantum oscillators. NPJ Quantum Inf. 2023, 9, 64.
  40. Neural echo state network using oscillations of gas bubbles in water. Phys. Rev. E 2021, 105, 044206.
  41. Efficient implementations of Echo State Network cross-validation. Cogn. Comput. 2021. https://doi.org/10.1007/s12559-021-09849-2.
  42. Large-scale optical reservoir computing for spatiotemporal chaotic systems prediction. Phys. Rev. X 2020, 10, 041037.
  43. Reservoir computing based on solitary-like waves dynamics of liquid film flows: A proof of concept. EPL 2023, 142, 43001.
  44. Bollt, E. On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD. Chaos 2021, 31, 013108.
  45. Learning spatiotemporal chaos using next-generation reservoir computing. Chaos 2022, 32, 093137.
  46. Next-generation reservoir computing based on memristor array. Acta Phys. Sin. 2022, 71, 140701.
  47. Noise resistance of next-generation reservoir computing: a comparative study with high-order correlation computation. Nonlinear Dyn. 2023, 111, 14295–14308.
  48. A survey on reservoir computing and its interdisciplinary applications beyond traditional machine learning. IEEE Access 2023, 11, 81033–81070.
  49. A novel approach to minimal reservoir computing. Sci. Reps. 2023, 13, 12970.
  50. Nonlinear input transformations are ubiquitous in quantum reservoir computing. Neuromorph. Comput. Eng. 2022, 2, 014008.
  51. Kosevich, Y.A. Nonlinear sinusoidal waves and their superposition in anharmonic lattices. Phys. Rev. Lett. 1993, 71, 2058–2061.
  52. Temporal pattern recognition with delayed-feedback spin-torque nano-oscillators. Phys. Rep. Appl. 2019, 12, 024049.
  53. Reservoir computing using a spin-wave delay-line active-ring resonator based on yttrium-iron-garnet film. Phys. Rev. Appl. 2020, 13, 034057.
  54. Quantum reservoir computing with a single nonlinear oscillator. Phys. Rev. Res. 2021, 3, 013077.
  55. Exploring quantumness in quantum reservoir computing. Phys. Rev. A 2023, 108, 052427.
  56. A VLSI analog computer/math co-processor for a digital computer. In Proceedings of the ISSCC. 2005 IEEE International Digest of Technical Papers. Solid-State Circuits Conference, 2005., 2005, pp. 82–586 Vol. 1. https://doi.org/10.1109/ISSCC.2005.1493879.
  57. Sorokina, M. Multidimensional fiber echo state network analogue. J. Phys. Photonics 2020, 2, 044006.
  58. Computing with networks of nonlinear mechanical oscillators. PLoS ONE 2017, 12, e0178663.
  59. Pattern Recognition in a Bucket. In Proceedings of the Advances in Artificial Life; Banzhaf, W.; Ziegler, J.; Christaller, T.; Dittrich, P.; Kim, J.T., Eds.; Springer: Berlin, 2003; pp. 588–597.
  60. Thin liquid film as an optical nonlinear-nonlocal medium and memory element in integrated optofluidic reservoir computer. Adv. Photon. 2022, 4, 046005.
  61. A new paradigm of reservoir computing exploiting hydrodynamics. Phys. Fluids 2023, 35, 071703.
  62. Adamatzky, A. A brief history of liquid computers. Philos. Trans. R. Soc. B 2019, 374, 20180372.
  63. From Navier-Stokes millennium-prize problem to soft matter computing, 2022, [arXiv:math.AP/2212.01492].
  64. Fiber echo state network analogue for high-bandwidth dual-quadrature signal processing. Opt. Express 2019, 27, 2387–2395.
  65. Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: Role of network spectral radius. Phys. Rev. Research 2019, 1, 033056.
  66. Performance optimization of a reservoir computing system based on a solitary semiconductor laser under electrical-message injection. Appl. Opt. 2020, 59, 6932–6938.
  67. Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons. Phys. Rev. Lett. 2020, 125, 093901.
  68. Reservoir computing with solitons. New J. Phys. 2021, 23, 023013.
  69. Remoissenet, M. Waves Called Solitons: Concepts and Experiments; Springer, 1994.
  70. Solitary-like wave dynamics in thin liquid films over a vibrated inclined plane. Appl. Sci. 2022, 13, 1888.
  71. Nonlinear periodic and solitary rolling waves in falling two-layer viscous liquid films. Phys. Rev. Fluids 2023, 8, 064801.
  72. Solitary wave dynamics of film flows. Phys. Fluids 1994, 6, 1702–1712.
  73. On the change of form of long waves advancing in a rectangular canal, and on a new type of long stationary waves. Philos. Mag. 1895, 39, 422–443.
  74. ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks. In Proceedings of the ICANN 2020 - 29th International Conference on Artificial Neural Networks; , 2020.
  75. Dynamics of roll waves. J. Fluid Mech. 2004, 514, 1–33.
  76. Coupling light and sound: giant nonlinearities from oscillating bubbles and droplets. Nanophotonics 2019, 8, 367–390.
  77. Nonlinear transformation of sine wave within the framework of symmetric (2+4) KdV equation. Symmetry 2022, 14.
  78. Jenkins, A. Self-oscillation. Phys. Rep. 2013, 525, 167–222.
  79. The van der Pol physical reservoir computer. Neuromorph. Comput. Eng. 2023, 3, 024004.
  80. Minimum complexity Echo State Network. IEEE Trans. Neural Netw. 2011, 22, 131–144.
  81. Unveiling the role of plasticity rules in reservoir computing. Neurocomputing 2021, 461, 705–715.
  82. Lorenz, E.N. Deterministic nonperiodic flow. J. Atmos. Sci.. 1963, 20, 130–141.
  83. Rössler, O.E. An equation for continuous chaos. Phys. Lett. 1976, 57A, 397–398.
  84. Hénon, M. A two-dimensional mapping with a strange attractor. Commun. Math. Phys. 1976, 50, 69–77.
  85. Ikeda, K. Multiple-valued stationary state and its instability of the transmitted light by a ring cavity system. Opt. Commun. 1979, 30, 257–261.
  86. Oscillation and chaos in physiological control systems. Science 1977, 197, 287–289.
  87. Physical implementation of reservoir computing through electrochemical reaction. Adv. Sci. 2022, 9, 2104076.
  88. van der Made, P. Learning How to Learn: Neuromorphic AI Inference at the Edge. BrainChip White Paper 2022, p. 12. Accessed 01 January 2023.
  89. Brain-inspired computing needs a master plan. Nature 2022, 604, 255–260.
  90. Neuromorphic liquids, colloids, and gels: A review. ChemPhysChem 2023, 24, e202200390.
  91. Photonics for artificial intelligence and neuromorphic computing. Nat. Photon. 2020, 15, 102–114.
  92. Short-term stock price prediction based on echo state networks. Expert Syst. Appl. 2009, 36, 7313–7317.
  93. Stock price forecasting: An Echo State Network approach. Comput. Syst. Sci. Eng. 2021, 36, 509–520.
  94. Variety and volatility in financial markets. Phys. Rev. E 2000, 62, 6126–6134.
  95. A small-world topology enhances the echo state property and signal propagation in reservoir computing. Neural Netw. 2019, 112, 15–23.
  96. Learning function from structure in neuromorphic networks. Nat. Mach. Intell. 2021, 3, 771–786.
  97. Brain connectivity meets reservoir computing. PLoS Comput. Biol. 2022, 18, e1010639.
  98. A long short-term memory for AI applications in spike-based neuromorphic hardware. Nat. Mach. Intell. 2022, 4, 467–479.
  99. Sporns, O. The non-random brain: Efficiency, economy, and complex dynamics. Front. Comput. Neurosci. 2011, 5. https://doi.org/10.3389/fncom.2011.00005.
  100. Progress in brain computer interface: challenges and opportunities. Front. Syst. Neurosci. 2021, 15. https://doi.org/10.3389/fnsys.2021.578875.
  101. Nanoscale neural network using non-linear spin-wave interference. Nat. Commun. 2021, 12, 6422.
  102. Performance enhancement of a spin-wave-based reservoir computing system utilizing different physical conditions. Phys. Rev. Appl. 2023, 19, 034047.
  103. Maksymov, I.S. Artificial musical creativity enabled by nonlinear oscillations of a bubble acting as a physical reservoir computing system. Int. J. Unconv. Comput. 2023, 18, 269–289.
  104. Lauterwasser, A. Water Sound Images: The Creative Music of the Universe; MACROmedia, San Francisco, 2007.
  105. Programmable DNA-based Boolean logic microfluidic processing unit. ACS Nano 2021, 15, 11644–11654.
  106. An organic artificial spiking neuron for in situ neuromorphic sensing and biointerfacing. Nat. Electron. 2022, 5, 774–783.
  107. Excitation of Faraday-like body waves in vibrated living earthworms. Sci. Rep. 2020, 10, 8564.
  108. Envisioning Arduino action: A collaborative tool for physical computing in educational settings. Int. J. Child Comput. Interact. 2021, 29, 100277.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets