Skip to main content
SpringerLink
Log in

Analysing the Limitations of Deep Learning for Developmental Robotics

  • Conference paper
  • First Online:
Biomimetic and Biohybrid Systems (Living Machines 2017)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10384))

Included in the following conference series:

Abstract

Deep learning is a powerful approach to machine learning however its inherent disadvantages leave much to be desired in the pursuit of the perfect learning machine. This paper outlines the multiple disadvantages of deep learning and offers a view into the implications to solving these problems and how this would affect the state of the art not only in developmental learning but also in real world applications.

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. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

    Google Scholar 

  2. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Reognition, pp. 580–587 (2014)

    Google Scholar 

  3. Graves, A., Mohamed, A.r., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (icassp), pp. 6645–6649. IEEE (2013)

    Google Scholar 

  4. van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., Kavukcuoglu, K.: Wavenet: A generative model for raw audio. CoRR abs/1609.03499 (2016)

    Google Scholar 

  5. Arik, S.O., Chrzanowski, M., Coates, A., Diamos, G., Gibiansky, A., Kang, Y., Li, X., Miller, J., Raiman, J., Sengupta, S., et al.: Deep voice: Real-time neural text-to-speech. arXiv preprint (2017). arXiv:1702.07825

  6. Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS P), pp. 372–387 (2016)

    Google Scholar 

  7. Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427–436 (2015)

    Google Scholar 

  8. Koopman, P., Wagner, M.: Challenges in autonomous vehicle testing and validation. SAE Int. J. Transp. Saf. 4(2016—-01–0128), 15–24 (2016)

    Article  Google Scholar 

  9. Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)

    Article  Google Scholar 

  10. McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: The sequential learning problem. Psychol. Learn. Motiv. 24, 109–165 (1989)

    Article  Google Scholar 

  11. Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint (2013). arXiv:1312.6211

  12. Fernando, C., Banarse, D., Blundell, C., Zwols, Y., Ha, D., Rusu, A.A., Pritzel, A., Wierstra, D.: Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint (2017). arXiv:1701.08734

  13. Kahneman, D.: Thinking, Fast and Slow. Macmillan, New York (2011)

    Google Scholar 

  14. Wheeler, M.E., Petersen, S.E., Buckner, R.L.: Memory’s echo: Vivid remembering reactivates sensory-specific cortex. Proc. Nat. Acad. Sci. 97(20), 11125–11129 (2000)

    Article  Google Scholar 

  15. Wolfe, J.M.: Guided search 2.0 a revised model of visual search. Psychon. Bull. Rev. 1(2), 202–238 (1994)

    Article  Google Scholar 

  16. Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint (2015). arXiv:1511.06434

Download references

Author information

Authors and Affiliations

  1. Psychology Department, University of Sheffield, Western Bank, Sheffield, UK

    Daniel Camilleri & Tony Prescott

Authors
  1. Daniel Camilleri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tony Prescott
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Daniel Camilleri .

Editor information

Editors and Affiliations

  1. University of Lincoln, Lincoln, United Kingdom

    Michael Mangan

  2. Stanford University, Stanford, California, USA

    Mark Cutkosky

  3. Universitat Pompeu Fabra, Barcelona, Spain

    Anna Mura

  4. Universitat Pompeu Fabra, Barcelona, Spain

    Paul F.M.J. Verschure

  5. University of Sheffield, Sheffield, United Kingdom

    Tony Prescott

  6. Bristol University, Bristol, United Kingdom

    Nathan Lepora

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Camilleri, D., Prescott, T. (2017). Analysing the Limitations of Deep Learning for Developmental Robotics. In: Mangan, M., Cutkosky, M., Mura, A., Verschure, P., Prescott, T., Lepora, N. (eds) Biomimetic and Biohybrid Systems. Living Machines 2017. Lecture Notes in Computer Science(), vol 10384. Springer, Cham. https://doi.org/10.1007/978-3-319-63537-8_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-63537-8_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-63536-1

  • Online ISBN: 978-3-319-63537-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation