Skip to main content

2016 | OriginalPaper | Buchkapitel

Exploiting Heterogeneous Units for Reservoir Computing with Simple Architecture

verfasst von : Gouhei Tanaka, Ryosho Nakane, Toshiyuki Yamane, Daiju Nakano, Seiji Takeda, Shigeru Nakagawa, Akira Hirose

Erschienen in: Neural Information Processing

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

Reservoir computing is a computational framework suited for sequential data processing, consisting of a reservoir part and a readout part. Not only theoretical and numerical studies on reservoir computing but also its implementation with physical devices have attracted much attention. In most studies, the reservoir part is constructed with identical units. However, a variability of physical units is inevitable, particularly when implemented with nano/micro devices. Here we numerically examine the effect of variability of reservoir units on computational performance. We show that the heterogeneity in reservoir units can be beneficial in reducing the prediction error in the reservoir computing system with a simple cycle reservoir.

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 Haykin, S.: Neural Networks. A Comprehensive Foundation, 2nd edn. Prentice Hall, Englewood Cliffs (1998)MATH Haykin, S.: Neural Networks. A Comprehensive Foundation, 2nd edn. Prentice Hall, Englewood Cliffs (1998)MATH
2.
Zurück zum Zitat Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach. GMD-Forschungszentrum Informationstechnik (2002) Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach. GMD-Forschungszentrum Informationstechnik (2002)
3.
Zurück zum Zitat Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007) Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007)
4.
Zurück zum Zitat LukošEvičIus, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)CrossRefMATH LukošEvičIus, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)CrossRefMATH
5.
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, Bonn, Germany 34 (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, Bonn, Germany 34 (2001)
6.
Zurück zum Zitat Jaeger, H.: Short term memory in echo state networks. GMD-Forschungszentrum Informationstechnik (2001) Jaeger, H.: Short term memory in echo state networks. GMD-Forschungszentrum Informationstechnik (2001)
7.
Zurück zum Zitat Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: Advances in neural information processing systems, pp. 593–600 (2002) Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: Advances in neural information processing systems, pp. 593–600 (2002)
8.
Zurück zum Zitat Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)CrossRefMATH Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)CrossRefMATH
9.
Zurück zum Zitat Paquot, Y., Duport, F., Smerieri, A., Dambre, J., Schrauwen, B., Haelterman, M., Massar, S.: Optoelectronic reservoir computing. Scientific Reports 2, 287 (2012) Paquot, Y., Duport, F., Smerieri, A., Dambre, J., Schrauwen, B., Haelterman, M., Massar, S.: Optoelectronic reservoir computing. Scientific Reports 2, 287 (2012)
10.
Zurück zum Zitat Kulkarni, M.S., Teuscher, C.: Memristor-based reservoir computing. In: 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), pp. 226–232 (2012) Kulkarni, M.S., Teuscher, C.: Memristor-based reservoir computing. In: 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), pp. 226–232 (2012)
11.
Zurück zum Zitat Katayama, Y., Yamane, T., Nakano, D., Nakane, R., Tanaka, G.: Wave-based neuromorphic computing framework for brain-like energy efficiency and integration. IEEE Trans. Nanotechnology (Accepted) Katayama, Y., Yamane, T., Nakano, D., Nakane, R., Tanaka, G.: Wave-based neuromorphic computing framework for brain-like energy efficiency and integration. IEEE Trans. Nanotechnology (Accepted)
12.
Zurück zum Zitat Yamane, T., Katayama, Y., Nakane, R., Tanaka, G., Nakano, D.: Wave-based reservoir computing by synchronization of coupled oscillators. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) Neural Information Processing, pp. 198–205. Springer, Switzerland (2015)CrossRef Yamane, T., Katayama, Y., Nakane, R., Tanaka, G., Nakano, D.: Wave-based reservoir computing by synchronization of coupled oscillators. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) Neural Information Processing, pp. 198–205. Springer, Switzerland (2015)CrossRef
13.
Zurück zum Zitat Rodan, A., Tiňo, P.: Minimum complexity echo state network. IEEE Trans. Neural Netw. 22(1), 131–144 (2011)CrossRef Rodan, A., Tiňo, P.: Minimum complexity echo state network. IEEE Trans. Neural Netw. 22(1), 131–144 (2011)CrossRef
14.
Zurück zum Zitat Mackey, M.C., Glass, L.: Oscillation and chaos in physiological control systems. Science 197(4300), 287–289 (1977)CrossRef Mackey, M.C., Glass, L.: Oscillation and chaos in physiological control systems. Science 197(4300), 287–289 (1977)CrossRef
15.
Zurück zum Zitat Wyffels, F., Schrauwen, B., Verstraeten, D., Stroobandt, D.: Band-pass reservoir computing. In: IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 3204–3209. IEEE (2008) Wyffels, F., Schrauwen, B., Verstraeten, D., Stroobandt, D.: Band-pass reservoir computing. In: IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 3204–3209. IEEE (2008)
16.
Zurück zum Zitat Weigend, A., Gershenfeld, N.: Time series prediction: forecasting the future and understanding the past. In: Proceedings of a NATO Advanced Research Workshop on Comparative Time Series Analysis, held in Santa Fe, New Mexico (1994) Weigend, A., Gershenfeld, N.: Time series prediction: forecasting the future and understanding the past. In: Proceedings of a NATO Advanced Research Workshop on Comparative Time Series Analysis, held in Santa Fe, New Mexico (1994)
Metadaten
Titel
Exploiting Heterogeneous Units for Reservoir Computing with Simple Architecture
verfasst von
Gouhei Tanaka
Ryosho Nakane
Toshiyuki Yamane
Daiju Nakano
Seiji Takeda
Shigeru Nakagawa
Akira Hirose
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-46687-3_20