Skip to main content
Springer Nature Link
Log in

Object Recognition Using Hierarchical Temporal Memory

  • Conference paper
  • First Online:
Intelligent Computing Systems (ISICS 2018)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 820))

Included in the following conference series:

Abstract

At this time, great effort is being directed toward developing problem-solving technology that mimic human cognitive processes. Research has been done to develop object recognition using Computer Vision for daily tasks such as secure access, traffic management, and robotic behavior. For this research, four different machine learning algorithms have been developed to overcome the computer vision problem of object recognition. Hierarchical temporal memory (HTM) is an emerging technology based on biological methods of the human cortex to learn patterns. This research applied an HTM algorithm to images (video sequences) in order to compare this technique against two others: support vector machines (SVM) and artificial neural networks (ANN). It was concluded that HTM was the most effective.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    In the HTM terminology, cells are synonyms of neurons.

  2. 2.

    The terms level and region will be used interchangeably.

  3. 3.

    Hebbian Theory defined by Gerstner [22].

  4. 4.

    “The accuracy is the proportion of true results (both true positives and true negatives) among the total number of cases examined” [5].

  5. 5.

    Numenta is the enterprise behind of the HTM technology.

  6. 6.

    Quartile: they are the values that divide a list of numbers into quarters.

References

  1. Jalal, A.S., Singh, V.: Visual object tracking: state of art. Int. J. Comput. Inform. 3, 227–247 (2011). Ljubljana, Slovenia

    Google Scholar 

  2. Hawkins, J., Blakeslee, S.: On Intelligence. St. Martin’s Griffin, USA (2005)

    Google Scholar 

  3. Fan, J., Xu, W., Gong, Y.: Convolutional neural networks: human traffic. IEEE Trans. About Neural Netw., 1610–1623 (2010). https://doi.org/10.1109/TNN.2010.2066286

  4. Hawkins, J., Ahmad, S., Dubinsky, D.: Cortical Learning Algorithms and HTM. Numenta Inc., California (2011)

    Google Scholar 

  5. Metz, C.E.: Principles of ROC Analysis. University of Chicago and the Franklin McLean Memorial Research Institute, Chicago, USA, pp. 283–298 (1978). 0001-2998/78/0804-0003S02.00/0

    Google Scholar 

  6. Lowe, D.G.: Object recognition based on local scale invariant features. In: Computer Vision: International Conference, pp. 1150–1157. IEEE, Canada (1999). https://doi.org/10.1109/ICCV.1999.790410

  7. Solem, J.E.: Python: Basics on Computer Vision. O’Reilly Medias, Sebastopol (2012)

    Google Scholar 

  8. Hassner, T., Mayzels, V., Zelnik-Manor, L.: About SIFT and its scale. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Rhode Island, USA (2012)

    Google Scholar 

  9. Han, B., Li, D., Ji, J.: DSIFT Algorithm for People Detection. Stanford University, California (2011)

    Google Scholar 

  10. Costa, A.: A MNIST Classifier Using OPF (2016). http://github.com/allanino/nupic-classifier-mnist

  11. Altman, N.S.: Introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat. 46, 175–185 (1992)

    MathSciNet  Google Scholar 

  12. Schaul, T., Bayer, J., Wierstra, D., Sun, Y., Felder, M., Sehnke, F., Rückstieß, T., Schmidhuber, J.: The PyBrain library. J. Mach. Learn. Res. 11, 743–746 (2011)

    Google Scholar 

  13. Bishop, C.M.: Pattern Recognition Using Neural Networks. Oxford University Press, Oxford (1995)

    Google Scholar 

  14. Blum, A.: Neural Networks (C++). Wiley, New York (1992)

    Google Scholar 

  15. Numenta: Nupic: managing vision tasks (2017). http://github.com/numenta

  16. Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2017). http://www.csie.ntu.edu.tw/cjlin/libsvm/

  17. Ihaka, R.: History of R: Past and Future. The University of Auckland, Auckland (1998)

    Google Scholar 

  18. Ferré, J., Rius, X.: Introduction to the Statistical Design of Experiments. Universitat Rovira i Virgili, Tarragona (2001)

    Google Scholar 

  19. Anderson, M., Whitcomb, P.: Design of Experiments: A Simplified Approach. Taylor and Francis Group, Boca Raton (2007)

    Google Scholar 

  20. Massart, D.L., Smeyers-Verbeke, J., Capron, X., Schlesier, K.: Means of Box Plots: Visual Presentation of Data. Vrije Universiteit Brussel, Brussel, Belgium (2005)

    Google Scholar 

  21. Schlag, I.: On Hierarchical Temporal Memory (2016). http://ischlag.github.io/2016/04/25/on-hierarchical-temporal-memory

  22. Gerstner, W.: Hebbian learning and plasticity. From Neuron to Cognition via Computational Neuroscience, Chap. 9. MIT Press, Cambridge (2011)

    Google Scholar 

Download references

Acknowledgements

We would like to thank our colleagues from the Happy Few Research Group for their support during the development of this research. In addition, we thank the PARMA Group for its guidance and support publishing this research.

Author information

Authors and Affiliations

  1. Universidad de Costa Rica, Cartago, Costa Rica

    Fabián Fallas-Moya

  2. Instituto Tecnológico de Costa Rica, Cartago, Costa Rica

    Francisco Torres-Rojas

Authors
  1. Fabián Fallas-Moya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Francisco Torres-Rojas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fabián Fallas-Moya .

Editor information

Editors and Affiliations

  1. Autonomous University of Yucatán, Merida, Mexico

    Carlos Brito-Loeza

  2. Autonomous University of Yucatán, Merida, Mexico

    Arturo Espinosa-Romero

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer International Publishing AG, part of Springer Nature

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Fallas-Moya, F., Torres-Rojas, F. (2018). Object Recognition Using Hierarchical Temporal Memory. In: Brito-Loeza, C., Espinosa-Romero, A. (eds) Intelligent Computing Systems. ISICS 2018. Communications in Computer and Information Science, vol 820. Springer, Cham. https://doi.org/10.1007/978-3-319-76261-6_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-76261-6_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-76260-9

  • Online ISBN: 978-3-319-76261-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics