Skip to main content
SpringerLink
Log in
Book cover

INNS Big Data and Deep Learning conference

INNSBDDL 2019: Recent Advances in Big Data and Deep Learning pp 196–205Cite as

Regularizing Neural Networks with Gradient Monitoring

  • 1004 Accesses

Part of the Proceedings of the International Neural Networks Society book series (INNS,volume 1)

Abstract

Neural networks are the most evolving artificial intelligence method in recent times and have been used for the most complex cognitive tasks. The success of these models has re-scripted many of the benchmark tests in a wide array of fields such as image recognition, natural language processing and speech recognition. The state of the art models leverage on a large amount of labelled training data and a complex model with a huge number of parameters to achieve good results. In this paper, we present a regularization methodology for reducing the size of these complex models while still maintaining generalizability of shallow and deep neural networks. The regularization is based on the monitoring of partial gradients of the loss function with respect to weight parameters. Another way to look at it is the percentage learning evident in a mini-batch training epoch and thereafter removing the weight connections where a certain percentage of learning is not evident. Subsequently, the method is evaluated on several benchmark classification tasks with a drastically smaller size and better performance to models trained with other similar regularization technique of DropConnect.

Keywords

  • Gradient monitoring
  • Regularization
  • Neural Networks

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   169.99
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. Bezdek, J.C., Keller, J.M., Krishnapuram, R., Kuncheva, L.I., Pal, N.R.: Will the real iris data please stand up? IEEE Trans. Fuzzy Syst. 7(3), 368–369 (1999). https://doi.org/10.1109/91.771092

    CrossRef  Google Scholar 

  2. Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 (2015)

  3. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)

    Google Scholar 

  4. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, vol. 1. MIT Press Cambridge, Cambridge (2016)

    MATH  Google Scholar 

  5. Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural comput. 18(7), 1527–1554 (2006)

    CrossRef  MathSciNet  Google Scholar 

  6. Kingma, D.P., Ba, J.L.: Adam: Amethod for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2014)

    Google Scholar 

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

    CrossRef  Google Scholar 

  8. LeCun, Y., Cortes, C., Burges, C.J.: MNIST handwritten digit database. AT&T Labs2 (2010). http://yann.lecun.com/exdb/mnist

  9. Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the ICML, vol. 30, p. 3 (2013)

    Google Scholar 

  10. Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)

    Google Scholar 

  11. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  12. Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066 (2013)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Automation Technology, Southwestphalia University of Applied Sciences, Soest, Germany

    Gavneet Singh Chadha, Elnaz Meydani & Andreas Schwung

Authors
  1. Gavneet Singh Chadha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Elnaz Meydani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andreas Schwung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gavneet Singh Chadha .

Editor information

Editors and Affiliations

  1. Department of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genova, Genoa, Italy

    Luca Oneto

  2. Department of Mathematics, University of Padova, Padua, Italy

    Nicolò Navarin

  3. Department of Mathematics, University of Padova, Padua, Italy

    Alessandro Sperduti

  4. Department of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genova, Genoa, Italy

    Davide Anguita

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chadha, G.S., Meydani, E., Schwung, A. (2020). Regularizing Neural Networks with Gradient Monitoring. In: Oneto, L., Navarin, N., Sperduti, A., Anguita, D. (eds) Recent Advances in Big Data and Deep Learning. INNSBDDL 2019. Proceedings of the International Neural Networks Society, vol 1. Springer, Cham. https://doi.org/10.1007/978-3-030-16841-4_21

Download citation

search

Navigation