Reservoir Computing Trends

Abstract

Reservoir Computing (RC) is a paradigm of understanding and training Recurrent Neural Networks (RNNs) based on treating the recurrent part (the reservoir) differently than the readouts from it. It started ten years ago and is currently a prolific research area, giving important insights into RNNs, practical machine learning tools, as well as enabling computation with non-conventional hardware. Here we give a brief introduction into basic concepts, methods, insights, current developments, and highlight some applications of RC.

This is a preview of subscription content, access via your institution.

Fig. 1

References

  1. 1.

    Atiya AF, Parlos AG (2000) New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans Neural Netw 11(3):697–709

    Article  Google Scholar 

  2. 2.

    Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166

    Article  Google Scholar 

  3. 3.

    Bernacchia A, Seo H, Lee D, Wang XJ (2011) A reservoir of time constants for memory traces in cortical neurons. Nat Neurosci 14(3):366–372

    Article  Google Scholar 

  4. 4.

    Buesing L, Bill J, Nessler B, Maass W (2011) Neural dynamics as sampling: a model for stochastic computation in recurrent networks of spiking neurons. PLoS Comput Biol 7(11):e1002211

    MathSciNet  Article  Google Scholar 

  5. 5.

    Bunke H, Varga T (2007) Off-line roman cursive handwriting recognition. In: Chaudhuri BB (ed) Digital document processing, advances in pattern recognition. Springer, Berlin, pp 165–183

    Google Scholar 

  6. 6.

    Buonomano DV, Maass W (2009) State-dependent computations: spatiotemporal processing in cortical networks. Nat Rev, Neurosci 10(2):113–125. http://www.ncbi.nlm.nih.gov/pubmed/19145235

    Article  Google Scholar 

  7. 7.

    Buteneers P, Verstraeten D, van Mierlo P, Wyckhuys T, Stroobandt D, Raedt R, Hallez H, Schrauwen B (2011) Automatic detection of epileptic seizures on the intra-cranial electroencephalogram of rats using reservoir computing. Artif Intell Med 53(3):215–223

    Article  Google Scholar 

  8. 8.

    Dominey PF (1995) Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning. Biol Cybern 73:265–274

    MATH  Article  Google Scholar 

  9. 9.

    Dominey PF (2005) From sensorimotor sequence to grammatical construction: evidence from simulation and neurophysiology. Adapt Behav 13(4):347–361

    Article  Google Scholar 

  10. 10.

    Dominey PF, Ramus F (2000) Neural network processing of natural language. I. Sensitivity to serial, temporal and abstract structure of language in the infant. Lang Cogn Processes 15(1):87–127

    Article  Google Scholar 

  11. 11.

    Doya K (1992) Bifurcations in the learning of recurrent neural networks. In: Proceedings of IEEE international symposium on circuits and systems 1992, vol 6, pp 2777–2780

    Google Scholar 

  12. 12.

    Fernando C, Sojakka S (2003) Pattern recognition in a bucket. In: Proceedings of the 7th European conference on advances in artificial life (ECAL 2003). LNCS, vol 2801. Springer, Berlin, pp 588–597

    Google Scholar 

  13. 13.

    Hermans M, Schrauwen B (2012) Recurrent kernel machines: computing with infinite echo state networks. Neural Comput 24(1):104–133. doi:10.1162/NECO_a_00200

    MathSciNet  MATH  Article  Google Scholar 

  14. 14.

    Hinaut X, Dominey PF (2011) A three-layered model of primate prefrontal cortex encodes identity and abstract categorical structure of behavioral sequences. J Physiol 105(1–3):16–24

    Google Scholar 

  15. 15.

    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  16. 16.

    Ijspeert AJ (2008) Central pattern generators for locomotion control in animals and robots: a review. Neural Netw 21:642–653

    Article  Google Scholar 

  17. 17.

    Ilies I, Jaeger H, Kosuchinas O, Rincon M, Šakėnas V, Vaškevičius N (2007) Stepping forward through echoes of the past: forecasting with echo state networks. http://www.neural-forecasting-competition.com/downloads/NN3/methods/27-NN3_Herbert_Jaeger_report.pdf. Short report on the winning entry to the NN3 financial forecasting competition

  18. 18.

    Jaeger H (2000) A method for supervised teaching of a recurrent artificial neural network. International patent. http://www.wipo.int/patentscope/search/en/WO2002031764

  19. 19.

    Jaeger H (2001) The “echo state” approach to analysing and training recurrent neural networks. Tech Rep GMD report 148, German National Research Center for Information Technology. http://www.faculty.jacobs-university.de/hjaeger/pubs/EchoStatesTechRep.pdf

  20. 20.

    Jaeger H (2002) Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the echo state network approach. GMD Report 159, Fraunhofer Institute AIS. http://minds.jacobs-university.de/pubs

  21. 21.

    Jaeger H (2007) Echo state network. Scholarpedia 2(9):2330. http://www.scholarpedia.org/article/Echo_state_network

    Article  Google Scholar 

  22. 22.

    Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667):78–80. doi:10.1126/science.1091277

    Article  Google Scholar 

  23. 23.

    Jaeger H, Lukoševičius M, Popovici D, Siewert U (2007) Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw 20(3):335–352

    MATH  Article  Google Scholar 

  24. 24.

    Jalalvand A, Triefenbach F, Verstraeten D, Martens JP (2011) Connected digit recognition by means of reservoir computing. In: Proceedings of interspeech 2011, pp 1725–1728

    Google Scholar 

  25. 25.

    Kindermans PJ, Buteneers P, Verstraeten D, Schrauwen B (2010) An uncued brain-computer interface using reservoir computing. In: Proceedings of the workshop on machine learning for assistive technologies

    Google Scholar 

  26. 26.

    Larger L, Soriano MC, Brunner D, Appeltant L, Gutierrez JM, Pesquera L, Mirasso CR, Fischer I (2012) Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. Opt Express 20:3241–3249. doi:10.1364/OE.20.003241

    Article  Google Scholar 

  27. 27.

    Legenstein R, Chase SM, Schwartz AB, Maass W (2010) A reward-modulated hebbian learning rule can explain experimentally observed network reorganization in a brain control task. J Neurosci 30(25):8400–8410

    Article  Google Scholar 

  28. 28.

    Li J, Jaeger H (2011) Minimal energy control of an ESN pattern generator. Technical report 26, Jacobs University Bremen, School of Engineering and Science

  29. 29.

    Lukoševičius M (2011) Reservoir computing and self-organized neural hierarchies. PhD Thesis, Jacobs University Bremen, Bremen, Germany

  30. 30.

    Lukoševičius M, Jaeger H (2009) Reservoir computing approaches to recurrent neural network training. Comput Sci Rev 3(3):127–149. doi:10.1016/j.cosrev.2009.03.005

    Article  Google Scholar 

  31. 31.

    Lukoševičius M, Popovici D, Jaeger H, Siewert U (2006) Time warping invariant echo state networks. IUB technical report 2, International University Bremen. http://minds.jacobs-university.de/pubs

  32. 32.

    Maass W (2011) Motivation, theory, and applications of liquid state machines. In: Cooper B, Sorbi A (eds) Computability in context: computation and logic in the real world. Imperial College Press, London, pp 275–296

    Google Scholar 

  33. 33.

    Maass W, Joshi P, Sontag E (2007) Computational aspects of feedback in neural circuits. PLoS Comput Biol 3(1):1–20

    MathSciNet  Article  Google Scholar 

  34. 34.

    Maass W, Natschläger T, Markram H (2002) Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput 14(11):2531–2560. doi:10.1162/089976602760407955

    MATH  Article  Google Scholar 

  35. 35.

    Martens J, Sutskever I (2011) Learning recurrent neural networks with Hessian-free optimization. In: Proc 28th int conf on machine learning. http://www.icml-2011.org/papers/532_icmlpaper.pdf

    Google Scholar 

  36. 36.

    Paquot Y, Duport F, Smerieri A, Dambre J, Schrauwen B, Haelterman M, Massar S (2012) Optoelectronic reservoir computing. Sci Rep 2:287. doi:10.1038/srep00287. http://www.nature.com/srep/2012/120227/srep00287/full/srep00287.html

    Article  Google Scholar 

  37. 37.

    Salmen M, Plöger P (2005) Echo state networks used for motor control. In: Proc IEEE int conf on robotics and automation (ICRA), pp 1953–1958

    Google Scholar 

  38. 38.

    Schiller UD, Steil JJ (2005) Analyzing the weight dynamics of recurrent learning algorithms. Neurocomputing 63C:5–23

    Article  Google Scholar 

  39. 39.

    Schrauwen B, D‘Haene M, Verstraeten D, Stroobandt D (2008) Compact hardware liquid state machines on FPGA for real-time speech recognition. Neural Netw 21(2–3):511–523

    Article  Google Scholar 

  40. 40.

    Schürmann F, Meier K, Schemmel J (2005) Edge of chaos computation in mixed-mode VLSI—a hard liquid. In: Advances in neural information processing systems (NIPS 2004), vol 17. MIT Press, Cambridge, pp 1201–1208

    Google Scholar 

  41. 41.

    Shi Z, Han M (2007) Support vector echo-state machine for chaotic time-series prediction. IEEE Trans Neural Netw 18(2):359–372

    Article  Google Scholar 

  42. 42.

    Skowronski MD, Harris JG (2007) Automatic speech recognition using a predictive echo state network classifier. Neural Netw 20(3):414–423. doi:10.1016/j.neunet.2007.04.006

    MATH  Article  Google Scholar 

  43. 43.

    Steil JJ (2004) Backpropagation-decorrelation: recurrent learning with O(N) complexity. In: Proceedings of the IEEE international joint conference on neural networks (IJCNN 2004), vol 2, pp 843–848

    Google Scholar 

  44. 44.

    Stieg AZ, Avizienis AV, Sillin HO, Martin-Olmos C, Aono M, Gimzewski JK (2012) Emergent criticality in complex Turing B-type atomic switch networks. Adv Mater 24(2):286–293. doi:10.1002/adma.201103053

    Article  Google Scholar 

  45. 45.

    Sussillo D, Abbott LF (2009) Generating coherent patterns of activity from chaotic neural networks. Neuron 63(4):544–557. doi:10.1016/j.neuron.2009.07.018

    Article  Google Scholar 

  46. 46.

    Triefenbach F, Jalalvand A, Schrauwen B, Martens JP (2010) Phoneme recognition with large hierarchical reservoirs. In: Advances in neural information processing systems (NIPS 2010), vol 23. MIT Press, Cambridge, pp 2307–2315. 2011

    Google Scholar 

  47. 47.

    Vandoorne K, Dierckx W, Schrauwen B, Verstraeten D, Baets R, Bienstman P, Campenhout JV (2008) Toward optical signal processing using photonic reservoir computing. Opt Express 16(15):11182–11192

    Article  Google Scholar 

  48. 48.

    Verstraeten D (2009) Reservoir computing: computation with dynamical systems. PhD Thesis, Electronics and Information Systems, University of Ghent. http://organic.elis.ugent.be/biblio

  49. 49.

    Verstraeten D, Schrauwen B, D’Haene M, Stroobandt D (2007) An experimental unification of reservoir computing methods. Neural Netw 20(3):391–403

    MATH  Article  Google Scholar 

  50. 50.

    Verstraeten D, Schrauwen B, Stroobandt D (2006) Reservoir-based techniques for speech recognition. In: Proceedings of the IEEE international joint conference on neural networks (IJCNN 2006), pp 1050–1053

    Google Scholar 

  51. 51.

    Verstraeten D, Schrauwen B, Stroobandt D, Van Campenhout J (2005) Isolated word recognition with the liquid state machine: a case study. Inf Process Lett 95(6):521–528

    MATH  Article  Google Scholar 

  52. 52.

    Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560

    Article  Google Scholar 

  53. 53.

    Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280

    Article  Google Scholar 

Download references

Acknowledgements

The authors acknowledge support by the European FP7 project ORGANIC (http://reservoir-computing.org/organic). Patent note. The basic ESN architecture and algorithm are protected for commercial use by international patents held by the Fraunhofer Society [18].

Author information

Affiliations

Authors

Corresponding author

Correspondence to Mantas Lukoševičius.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Lukoševičius, M., Jaeger, H. & Schrauwen, B. Reservoir Computing Trends. Künstl Intell 26, 365–371 (2012). https://doi.org/10.1007/s13218-012-0204-5

Download citation

Keywords

  • Reservoir computing
  • Recurrent neural network
  • Echo state network