Skip to main content
SpringerLink
Log in

Deep Learning Framework Analysis

  • Chapter
  • First Online:
Deep Learning and Missing Data in Engineering Systems

Part of the book series: Studies in Big Data ((SBD,volume 48))

  • 1270 Accesses

Abstract

In this chapter, we investigate the effectiveness of using a deep autoencoder network with three and five hidden layers. These networks will be used in combination with optimization algorithms to perform missing data estimation tasks. The results from these networks will be compared against those obtained from using the seven hidden-layered deep autoencoder network from the literature. The network training times are observed to increase with the increasing number of hidden layers.

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 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover 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

  • Abdella, M., & Marwala, T. (2005). The use of genetic algorithms and neural networks to approximate missing data in database. In 3rd International Conference on Computational Cybernetics, (ICCC) (pp. 207–212). IEEE.

    Google Scholar 

  • Brain, L. B., Marwala, T., & Tettey, T. (2006). Autoencoder networks for HIV classification. Current Science, 91(11), 1467–1473.

    Google Scholar 

  • Finn C., Tan, X., Duan, Y., Darrell, T., Levine, S., & Abbeel, P. (2016). Deep spatial autoencoders for visuomotor learning. In International Conference on Robotics and Automation (ICRA) (pp. 512–519).

    Google Scholar 

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

    Article  MathSciNet  Google Scholar 

  • Jerez, J. M., Molina, I., Garcıa-Laencina, P. J., Alba, E., Ribelles, N., Martın, M., et al. (2010). Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artificial Intelligence in Medicine, 50(2), 105–115. Elsevier.

    Google Scholar 

  • Ju, Y., Guo, J., & Liu, S. (2015). A deep learning method combined sparse autoencoder with SVM. In International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) (pp. 257–260).

    Google Scholar 

  • Krizhevsky, A., & Hinton, G. E. (2011). Using very deep autoencoders for content based image retrieval. In 19th European Symposium on Artificial Neural Networks (ESANN). Bruges, Belgium, 27–29 April 2011.

    Google Scholar 

  • Leke, C., Twala, B., & Marwala, T. (2014). Modeling of missing data prediction: Computational intelligence and optimization algorithms. In International Conference on Systems, Man and Cybernetics (SMC) (pp. 1400–1404). IEEE.

    Google Scholar 

  • Leke, C., & Marwala, T. (2016). Missing data estimation in high-dimensional datasets: A Swarm intelligence-deep neural network approach. In International Conference in Swarm Intelligence (pp. 259–270). Springer International Publishing.

    Google Scholar 

  • Leke, C., Ndjiongue, A. R., Twala, B., & Marwala, T. (2017). A deep learning-cuckoo search method for missing data estimation in high-dimensional datasets. In International Conference in Swarm Intelligence (pp. 561–572). Springer, Cham.

    Google Scholar 

  • Liew, A. W.-C., Law, N.-F., & Yan, H. (2011). Missing value imputation for gene expression data: computational techniques to recover missing data from available information. Briefings in Bioinformatics, 12(5), 498–513. Oxford University Press.

    Article  Google Scholar 

  • Myers, T. A. (2011). Goodbye, listwise deletion: Presenting hot deck imputation as an easy and effective tool for handling missing data. Communication Methods and Measures, 5(4), 297–310. Taylor & Francis.

    Google Scholar 

  • Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the state of the art. Psychological Methods, 7(2), 147. American Psychological Association.

    Article  Google Scholar 

  • Ssali, G., & Marwala, T. (2007). Estimation of missing data using computational intelligence and decision trees. arXiv:0709.1640.

  • Van Buuren, S. (2012). Flexible imputation of missing data. CRC press.

    Google Scholar 

  • Vukosi, M. N., Nelwamondo, F. V., & Marwala, T. (2007). Autoencoder, principal component analysis and support vector regression for data imputation. arXiv:0709.2506.

  • Zhang, S. (2011). Shell-neighbor method and its application in missing data imputation. Applied Intelligence, 35(1), 123–133. Springer.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Engineering and Built Environment, University of Johannesburg, Auckland Park, South Africa

    Collins Achepsah Leke & Tshilidzi Marwala

Authors
  1. Collins Achepsah Leke
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tshilidzi Marwala
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Collins Achepsah Leke .

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Leke, C.A., Marwala, T. (2019). Deep Learning Framework Analysis. In: Deep Learning and Missing Data in Engineering Systems. Studies in Big Data, vol 48. Springer, Cham. https://doi.org/10.1007/978-3-030-01180-2_10

Download citation

Publish with us

Policies and ethics

Search

Navigation