Skip to main content
SpringerLink
Log in
Book cover

International Conference on Neural Information Processing

ICONIP 2016: Neural Information Processing pp 280–287Cite as

Automatic Design of Neural Network Structures Using AiS

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 9948))

Abstract

Structures of neural networks are usually designed by experts to fit target problems. This study proposes a method to automate small network design for a regression problem based on the Add-if-Silent (AiS) function used in the neocognitron. Because the original AiS is designed for image pattern recognition, this study modifies the intermediate function to be Radial Basis Function (RBF). This study shows that the proposed method can determine an optimized network structure using the Bike Sharing Dataset as one case study. The generalization performance is also shown.

This is a preview of subscription content, 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

Learn about institutional subscriptions

References

  1. Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)

    Article  MATH  Google Scholar 

  2. Hinton, G.E., Osindero, S., The, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  3. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)

  4. Fukushima, K.: Artificial vision by multi-layered neural networks: neocognitron and its advances. Neural Netw. 37, 103–109 (2013)

    Article  Google Scholar 

  5. Fukushima, K., Shouno, H.: Deep convolutional network neocognitron: improved interpolating-vector. In: International Joint Conference on Neural Networks 2015, Killarney, Ireland, pp. 1603–1610 (2015)

    Google Scholar 

  6. Hadi, F., Joao, G.: Event labeling combining ensemble detectors and background knowledge. Prog. Artif. Intell. 2, 1–15 (2013). Springer, Heidelberg

    Article  Google Scholar 

  7. Akaike, H.: Information theory and an extension of the maximum likelihood principle. In: Proceedings of the 2nd Informational Symposium on Information Theory, Akadimiai Kiado, Budapest, pp. 267–281 (1973)

    Google Scholar 

  8. Kim, S., Tadesse, M.G., Vannucci, M.: Variable selection in clustering via Dirichlet mixture models. Biometrika 93(4), 877–893 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  9. Kurihara, K., Welling, M., Vlassis, N.: Accelerated variational dirichlet process mixtures. In: NIPS (2006)

    Google Scholar 

  10. Hagiwara, K., Toda, N., Usui, S.: On the problem of applying AIC to determine the structure of a layered feedforward neural network. In: Proceedings of 1993 International Joint Conference on Neural Networks, Nagoya, pp. 2263–2266 (1993)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Mitsubishi Electric Corporation, Information Technology R&D Center, Kamakura, Kanagawa, Japan

    Toshisada Mariyama, Kunihiko Fukushima & Wataru Matsumoto

  2. Fuzzy Logic System Institute, Fukuoka, Japan

    Kunihiko Fukushima

Authors
  1. Toshisada Mariyama
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kunihiko Fukushima
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wataru Matsumoto
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Toshisada Mariyama .

Editor information

Editors and Affiliations

  1. The University of Tokyo, Tokyo, Japan

    Akira Hirose

  2. Kobe University, Kobe, Japan

    Seiichi Ozawa

  3. Okinawa Institute of Science and Technology Graduate University, Onna, Japan

    Kenji Doya

  4. Nara Institute of Science and Technology, Ikoma, Japan

    Kazushi Ikeda

  5. Kyungpook National University, Daegu, Korea (Republic of)

    Minho Lee

  6. Chinese Academy of Sciences, Beijing, China

    Derong Liu

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Mariyama, T., Fukushima, K., Matsumoto, W. (2016). Automatic Design of Neural Network Structures Using AiS. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9948. Springer, Cham. https://doi.org/10.1007/978-3-319-46672-9_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-46672-9_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-46671-2

  • Online ISBN: 978-3-319-46672-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation