Skip to main content
SpringerLink
Log in

Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer

  • Conference paper
  • First Online:
Book cover Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions (ICANN 2019)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 11731))

Included in the following conference series:

  • 5214 Accesses

Abstract

Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. Its photonic implementations have received much interest recently, and have been successfully applied to speech recognition and time-series forecasting. However, few works have been devoted to the more challenging computer vision tasks. In this work, we use a large-scale photonic reservoir computer for classification of handwritten digits from the MNIST database. We investigate and compare different feature extraction techniques (such as zoning, Gabor filters, and HOG) and report classification errors of 1% experimentally and \(0.8\%\) in numerical simulations.

Supported by AFOSR (grants No. FA-9550-15-1-0279 and FA-9550-17-1-0072), Région Grand-Est, and the Volkswagen Foundation via the NeuroQNet.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bahi, H.E., Mahani, Z., Zatni, A., Saoud, S.: A robust system for printed and handwritten character recognition of images obtained by camera phone. Technical report (2015). http://www.wseas.org/multimedia/journals/signal/2015/a045714-403.pdf

  2. Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013). https://doi.org/10.1109/tpami.2013.50

    Article  Google Scholar 

  3. Bueno, J., et al.: Reinforcement learning in a large-scale photonic recurrent neural network. Optica 5(6), 756 (2018). https://doi.org/10.1364/optica.5.000756

    Article  MathSciNet  Google Scholar 

  4. Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). https://doi.org/10.1007/bf00994018

    Article  MATH  Google Scholar 

  5. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2005). https://doi.org/10.1109/cvpr.2005.177

  6. Daugman, J.G.: Two-dimensional spectral analysis of cortical receptive field profiles. Vis. Res. 20(10), 847–856 (1980). https://doi.org/10.1016/0042-6989(80)90065-6

    Article  Google Scholar 

  7. Hagerstrom, A.M., Murphy, T.E., Roy, R., Hövel, P., Omelchenko, I., Schöll, E.: Experimental observation of chimeras in coupled-map lattices. Nat. Phys. 8(9), 658–661 (2012). https://doi.org/10.1038/nphys2372

    Article  Google Scholar 

  8. Hussain, A.B.S., Toussaint, G.T., Donaldson, R.W.: Results obtained using a simple character recognition procedure on Munson’s handprinted data. IEEE Trans. Comput. C–21(2), 201–205 (1972). https://doi.org/10.1109/tc.1972.5008927

    Article  Google Scholar 

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

    Article  Google Scholar 

  10. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539

    Article  Google Scholar 

  11. 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). https://doi.org/10.1162/089976602760407955

    Article  MATH  Google Scholar 

  12. Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986). https://doi.org/10.1007/bf00116251

    Article  Google Scholar 

  13. der Sande, G.V., Brunner, D., Soriano, M.C.: Advances in photonic reservoir computing. Nanophotonics 6(3) (2017). https://doi.org/10.1515/nanoph-2016-0132

  14. Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 1058–1066. PMLR, Atlanta, Georgia, USA, 17–19 June 2013 (2013)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. LMOPS EA 4423, CentraleSupélec, Université Paris-Saclay, 57070, Metz, France

    Piotr Antonik, Nicolas Marsal & Damien Rontani

  2. Université de Lorraine, CentraleSupélec, LMOPS, 57000, Metz, France

    Piotr Antonik, Nicolas Marsal & Damien Rontani

  3. FEMTO-ST Institute/Optics Department, CNRS & University Bourgogne Franche-Comté, 25030, Besançon, France

    Daniel Brunner

Authors
  1. Piotr Antonik
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nicolas Marsal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel Brunner
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Damien Rontani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Damien Rontani .

Editor information

Editors and Affiliations

  1. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Igor V. Tetko

  2. Institute of Computer Science, Czech Academy of Sciences, Prague 8, Czech Republic

    Věra Kůrková

  3. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Pavel Karpov

  4. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Fabian Theis

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Antonik, P., Marsal, N., Brunner, D., Rontani, D. (2019). Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science(), vol 11731. Springer, Cham. https://doi.org/10.1007/978-3-030-30493-5_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-30493-5_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-30492-8

  • Online ISBN: 978-3-030-30493-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation