Regularizing Neural Networks with Gradient Monitoring

  • Gavneet Singh ChadhaEmail author
  • Elnaz Meydani
  • Andreas Schwung
Conference paper
Part of the Proceedings of the International Neural Networks Society book series (INNS, volume 1)


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.


Gradient monitoring Regularization Neural Networks 


  1. 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). Scholar
  2. 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. 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. 4.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, vol. 1. MIT Press Cambridge, Cambridge (2016)zbMATHGoogle Scholar
  5. 5.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural comput. 18(7), 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  6. 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. 7.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). Scholar
  8. 8.
    LeCun, Y., Cortes, C., Burges, C.J.: MNIST handwritten digit database. AT&T Labs2 (2010).
  9. 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. 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. 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)MathSciNetzbMATHGoogle Scholar
  12. 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

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Gavneet Singh Chadha
    • 1
    Email author
  • Elnaz Meydani
    • 1
  • Andreas Schwung
    • 1
  1. 1.Department of Automation TechnologySouthwestphalia University of Applied SciencesSoestGermany

Personalised recommendations