Skip to main content
SpringerLink
Log in

SINN: Shepard Interpolation Neural Networks

  • Conference paper
  • First Online:
Advances in Visual Computing (ISVC 2016)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10073))

Included in the following conference series:

Abstract

A novel feed forward Neural Network architecture is proposed based on Shepard Interpolation. Shepard Interpolation is a method for approximating multi-dimensional functions with known coordinate-value pairs [4]. In a Shepard Interpolation Neural Network (SINN), weights and biases are deterministically initiated to non-zero values. Furthermore, Shepard networks maintain a similar accuracy as traditional Neural Networks with a reduction in memory footprint and number of hyper parameters such as number of layers, layer sizes and activation functions. Shepard Interpolation Networks greatly reduce the complexity of Neural Networks, improving performance while maintaining accuracy. The accuracy of Shepard Networks is evaluated on the MNIST digit recognition task. The proposed architecture is compared to LeCun et al. original work on Neural networks [9].

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. Haykin, S.: Neural networks: a comprehensive foundation. Neural Netw. 2(2004) (2004)

    Google Scholar 

  2. Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural networks 2(5), 359–366 (1989)

    Article  Google Scholar 

  3. Ren, J.S.J., et al.: Shepard convolutional neural networks. In: Advances in Neural Information Processing Systems (2015)

    Google Scholar 

  4. Shepard, D.: A two-dimensional interpolation function for irregularly-spaced data. In: Proceedings of the 1968 23rd ACM National Conference. ACM (1968)

    Google Scholar 

  5. “Metric (mathematics)”: Wikipedia: The Free Encyclopedia. Wikimedia Foundation, Inc., Web Date accessed 10 August 2016. https://en.wikipedia.org/wiki/Metric_(mathematics). Date last updated (21 August 2016)

  6. Gordon, W.J., Wixom, J.A.: Shepard’s method of “metric interpolation” to bivariate and multivariate interpolation. Math. Comput. 32(141), 253–264 (1978)

    MathSciNet  MATH  Google Scholar 

  7. Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015)

    Google Scholar 

  8. LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Google Scholar 

  9. Singer, S., Nelder, J.: Nelder-Mead algorithm. Scholarpedia 4(7), 2928 (2009)

    Article  Google Scholar 

  10. Glorot, X., Antoine, B., Yoshua, B.: Deep sparse rectifier neural networks. Aistats 15(106), 275 (2011)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Engineering, University of Ottawa, Ottawa, Canada

    Phillip Williams

Authors
  1. Phillip Williams
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Phillip Williams .

Editor information

Editors and Affiliations

  1. University of Nevada, Reno, Nevada, USA

    George Bebis

  2. NASA Ames Research Center, Moffett Field, California, USA

    Richard Boyle

  3. Lawrence Berkeley National Laboratory, Berkeley, California, USA

    Bahram Parvin

  4. Desert Research Institute, Reno, Nevada, USA

    Darko Koracin

  5. The Australian National University, O’Malley, Aust Capital Terr, Australia

    Fatih Porikli

  6. Pilot AI Labs, Redwood City, California, USA

    Sandra Skaff

  7. University of Florida, Gainesville, Florida, USA

    Alireza Entezari

  8. Google Inc., Mountain View, California, USA

    Jianyuan Min

  9. Osaka University, Osaka, Japan

    Daisuke Iwai

  10. The MOVES Institute, Monterey, California, USA

    Amela Sadagic

  11. University of Arizona, Tucson, Arizona, USA

    Carlos Scheidegger

  12. Université Paris-Sud, Orsay, France

    Tobias Isenberg

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Williams, P. (2016). SINN: Shepard Interpolation Neural Networks. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2016. Lecture Notes in Computer Science(), vol 10073. Springer, Cham. https://doi.org/10.1007/978-3-319-50832-0_34

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-50832-0_34

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-50831-3

  • Online ISBN: 978-3-319-50832-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation