Skip to main content

2020 | OriginalPaper | Buchkapitel

Quantifying Robustness and Capacity of Reservoir Computers with Consistency Profiles

verfasst von : Thomas Lymburn, Thomas Jüngling, Michael Small

Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2020

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We study the consistency property in reservoir computers with noise. Consistency quantifies the functional dependence of a driven dynamical system on its input via replica tests. We characterise the high-dimensional profile of consistency in typical reservoirs subject to intrinsic and measurement noise. An integral of the consistency is introduced to measure capacity and act as an effective size of the reservoir. We observe a scaling law in the dependency of the consistency capacity on the noise amplitude and reservoir size, and demonstrate how this measure of capacity explains performance.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Appeltant, L., et al.: Information processing using a single dynamical node as complex system. Nat. Commun. 2, 468 (2011)CrossRef Appeltant, L., et al.: Information processing using a single dynamical node as complex system. Nat. Commun. 2, 468 (2011)CrossRef
2.
Zurück zum Zitat Bueno, J., Brunner, D., Soriano, M.C., Fischer, I.: Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback. Opt. Exp. 25(3), 2401 (2017)CrossRef Bueno, J., Brunner, D., Soriano, M.C., Fischer, I.: Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback. Opt. Exp. 25(3), 2401 (2017)CrossRef
3.
5.
Zurück zum Zitat Dambre, J., Verstraeten, D., Schrauwen, B., Massar, S.: Information processing capacity of dynamical systems. Sci. Rep. 2, 514 (2012)CrossRef Dambre, J., Verstraeten, D., Schrauwen, B., Massar, S.: Information processing capacity of dynamical systems. Sci. Rep. 2, 514 (2012)CrossRef
6.
Zurück zum Zitat Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. German National Research Center for Information Technology GMD Technical Report 148 (2001) Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. German National Research Center for Information Technology GMD Technical Report 148 (2001)
7.
Zurück zum Zitat Jaeger, H.: Short term memory in echo state networks. German National Research Center for Information Technology GMD Technical Report 152 (2002) Jaeger, H.: Short term memory in echo state networks. German National Research Center for Information Technology GMD Technical Report 152 (2002)
8.
Zurück zum Zitat Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78 (2004)CrossRef Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78 (2004)CrossRef
9.
Zurück zum Zitat Jüngling, T., Soriano, M.C., Oliver, N., Porte, X., Fischer, I.: Consistency properties of chaotic systems driven by time-delayed feedback. Phys. Rev. E 97, 042202 (2018)CrossRef Jüngling, T., Soriano, M.C., Oliver, N., Porte, X., Fischer, I.: Consistency properties of chaotic systems driven by time-delayed feedback. Phys. Rev. E 97, 042202 (2018)CrossRef
11.
Zurück zum Zitat Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127 (2009)CrossRef Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127 (2009)CrossRef
12.
Zurück zum Zitat Lymburn, T., Khor, A., Stemler, T., Corréa, D.C., Small, M., Jüngling, T.: Consistency in echo-state networks. Chaos 29(2), 023118 (2019)CrossRef Lymburn, T., Khor, A., Stemler, T., Corréa, D.C., Small, M., Jüngling, T.: Consistency in echo-state networks. Chaos 29(2), 023118 (2019)CrossRef
13.
Zurück zum Zitat Nakayama, J., Kanno, K., Uchida, A.: Laser dynamical reservoir computing with consistency: an approach of a chaos mask signal. Opt. Exp. 24(8), 8679 (2016)CrossRef Nakayama, J., Kanno, K., Uchida, A.: Laser dynamical reservoir computing with consistency: an approach of a chaos mask signal. Opt. Exp. 24(8), 8679 (2016)CrossRef
14.
Zurück zum Zitat Oliver, N., Jüngling, T., Fischer, I.: Consistency properties of a chaotic semiconductor laser driven by optical feedback. Phys. Rev. Lett. 114, 123902 (2015)CrossRef Oliver, N., Jüngling, T., Fischer, I.: Consistency properties of a chaotic semiconductor laser driven by optical feedback. Phys. Rev. Lett. 114, 123902 (2015)CrossRef
15.
Zurück zum Zitat Pathak, J., Hunt, B., Girvan, M., Lu, Z., Ott, E.: Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Phys. Rev. Lett. 120, 024102 (2018)CrossRef Pathak, J., Hunt, B., Girvan, M., Lu, Z., Ott, E.: Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Phys. Rev. Lett. 120, 024102 (2018)CrossRef
16.
Zurück zum Zitat Rodan, A., Tino, P.: Minimum complexity echo state network. IEEE Trans. Neural Netw. 22(1), 131 (2011)CrossRef Rodan, A., Tino, P.: Minimum complexity echo state network. IEEE Trans. Neural Netw. 22(1), 131 (2011)CrossRef
17.
Zurück zum Zitat Schumacher, J., Haslinger, R., Pipa, G.: Statistical modeling approach for detecting generalized synchronization. Phys. Rev. E 85, 056215 (2012)CrossRef Schumacher, J., Haslinger, R., Pipa, G.: Statistical modeling approach for detecting generalized synchronization. Phys. Rev. E 85, 056215 (2012)CrossRef
18.
Zurück zum Zitat Semenova, N., Porte, X., Andreoli, L., Jacquot, M., Larger, L., Brunner, D.: Fundamental aspects of noise in analog-hardware neural networks. Chaos 29(10), 103128 (2019)MathSciNetCrossRef Semenova, N., Porte, X., Andreoli, L., Jacquot, M., Larger, L., Brunner, D.: Fundamental aspects of noise in analog-hardware neural networks. Chaos 29(10), 103128 (2019)MathSciNetCrossRef
19.
Zurück zum Zitat Soriano, M.C., Van der Sande, G., Fischer, I., Mirasso, C.R.: Synchronization in simple network motifs with negligible correlation and mutual information measures. Phys. Rev. Lett. 108, 134101 (2012)CrossRef Soriano, M.C., Van der Sande, G., Fischer, I., Mirasso, C.R.: Synchronization in simple network motifs with negligible correlation and mutual information measures. Phys. Rev. Lett. 108, 134101 (2012)CrossRef
20.
Zurück zum Zitat Tanaka, G.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100 (2019)CrossRef Tanaka, G.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100 (2019)CrossRef
21.
Zurück zum Zitat Uchida, A., McAllister, R., Roy, R.: Consistency of nonlinear system response to complex drive signals. Phys. Rev. Lett. 93, 244102 (2004)CrossRef Uchida, A., McAllister, R., Roy, R.: Consistency of nonlinear system response to complex drive signals. Phys. Rev. Lett. 93, 244102 (2004)CrossRef
Metadaten
Titel
Quantifying Robustness and Capacity of Reservoir Computers with Consistency Profiles
verfasst von
Thomas Lymburn
Thomas Jüngling
Michael Small
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-61616-8_36