Advertisement

Encoding Data to Use with a Sparse Distributed Memory

  • Mateus MendesEmail author
  • Manuel M. Crisóstomo
  • A. Paulo Coimbra
Chapter
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 60)

Abstract

A Sparse Distributed Memory (SDM) is a kind of associative memory suitable to work with high-dimensional vectors of random data. This memory model exhibits the characteristics of a large boolean space, which are to a great extent those of the human long-term memory. Hence, this model is attractive for Robotics and Artificial Intelligence, since it can possibly grant artificial machines those same characteristics. However, the original SDM model is appropriate to work with random data. Sensorial data is not always random: most of the times it is based on the Natural Binary Code and tends to cluster around some specific points. This means that the SDM performs poorer than expected. As part of an ongoing project, in which the goal is to navigate a robot using a SDM to store and retrieve sequences of images and associated path information, different methods of encoding the data were tested. Some methods perform better than others, and one method is presented that can offer the best performance and still maintain the characteristics of the original model.

Keywords

Associative memory sparse distributed memory SDM data encoding 

References

  1. 1.
    Bose, J.: A scalable sparse distributed neural memory model. Master’s thesis, University of Manchester, Faculty of Science and Engineering, Manchester, UK (2003)Google Scholar
  2. 2.
    Furber, S.B., Bainbridge, J., Cumpstey, J.M., Temple, S.: Sparse distributed memory using n-of-m codes. Neural Networks 17(10), 1437–1451 (2004)zbMATHCrossRefGoogle Scholar
  3. 3.
    Hely, T.A., Willshaw, D.J., Hayes, G.M.: A new approach to kanerva’s sparse distributed memories. IEEE Trans. Neural Networks (1999)Google Scholar
  4. 4.
    Jockel, S., Mendes, M., Zhang, J., Coimbra, A.P., Crisóstomo, M.M.: Robot navigation and manipulation based on a predictive associative memory. In: Proceedings of the 2009 IEEE 8th International Conference on Development and Learning (ICDL), Shanghai, China (2009)Google Scholar
  5. 5.
    Kanerva, P.: Sparse Distributed Memory. MIT Press, Cambridge (1988)zbMATHGoogle Scholar
  6. 6.
    Matsumoto, Y., Inaba, M., Inoue, H.: View-based approach to robot navigation. In: Proceedings of 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (2000)Google Scholar
  7. 7.
    Mendes, M., Coimbra, A.P., Crisóstomo, M.: AI and memory: Studies towards equipping a robot with a sparse distributed memory. In: Proceedings of the IEEE International Conference on Robotics and Biomimetics, Sanya, China (2007)Google Scholar
  8. 8.
    Mendes, M., Crisóstomo, M., Coimbra, A.P.: Robot navigation using a sparse distributed memory. In: Proceedings of the 2008 IEEE International Conference on Robotics and Automation, Pasadena, CA (2008)Google Scholar
  9. 9.
    Mendes, M., Crisóstomo, M., Coimbra, A.P.: Assessing a sparse distributed memory using different encoding methods. In: Proceedings of the 2009 International Conference of Computational Intelligence and Intelligent Systems, pp. 37–42. London, UK (2009)Google Scholar
  10. 10.
    Rao, Rajesh P.N., Fuentes, O.: Hierarchical learning of navigational behaviors in an autonomous robot using a predictive sparse distributed memory. Mach. Learn. 31(1–3), 87–113 (1998)zbMATHCrossRefGoogle Scholar
  11. 11.
    Ratitch, B., Precup, D.: Sparse distributed memories for on-line value-based reinforcement learning. In: ECML (2004)Google Scholar
  12. 12.
    Rogers, D.: Predicting weather using a genetic memory: a combination of kanerva’s sparse distributed memory with holland’s genetic algorithms. In: NIPS (1989)Google Scholar
  13. 13.
    Vanhala, J., Saarinen, J., Kaski, K.: Sparse distributed memory for multivalued patterns. In: IEEE Int. Conf. Neural Networks (1993)Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • Mateus Mendes
    • 1
    • 2
    Email author
  • Manuel M. Crisóstomo
    • 2
  • A. Paulo Coimbra
    • 2
  1. 1.ESTGOH, Polytechnic Institute of CoimbraOliveira do HospitalPortugal
  2. 2.Institute of Systems and Robotics, Pólo IIUniversity of CoimbraCoimbraPortugal

Personalised recommendations