Experiments with a Sparse Distributed Memory for Text Classification

  • Mateus Mendes
  • A. Paulo Coimbra
  • Manuel M. Crisóstomo
  • Jorge Rodrigues
Conference paper


The Sparse Distributed Memory (SDM) has been studied for decades as a theoretical model of an associative memory in many aspects similar to the human brain. It has been tested for different purposes. The present work describes its use as a quick text classifier, based on pattern similarity only. The results found with different datasets were superior to the performance of the dumb classifier or purely random choice, even without text preprocessing. Experiments were performed with a popular Reuters newsgroups dataset and also for real time web ad serving.


SDM Sparse distributed memory Text classification Text comparison Long range correlations Vector space model 


  1. 1.
    E.G. Altmanna, G. Cristadorob, M.D. Esposti, On the origin of long-range correlations in texts. Proc. Nat. Acad. Sci. U.S.A. 109(29) (2012)Google Scholar
  2. 2.
    P. Kanerva, Sparse Distributed Memory (MIT Press, Cambridge, 1988)MATHGoogle Scholar
  3. 3.
    D. Rogers, Predicting weather using a genetic memory: a combination of Kanerva’s sparse distributed memory with Holland’s genetic algorithms, in NIPS (1989)Google Scholar
  4. 4.
    M. Mendes, M.M. Crisóstomo, A. Paulo Coimbra, Robot navigation using a sparse distributed memory, in Proceedings of IEEE International Conference on Robotics and Automation, Pasadena, California, USA, May 2008Google Scholar
  5. 5.
    M. Mendes, A. Paulo Coimbra, M.M. Crisóstomo, Exploring long-range correlations for text classification using a sparse distributed memory, in Lecture Notes in Engineering and Computer Science, Proceedings of The World Congress on Engineering 2013, WCE 2013, London, U.K., 3–5 July 2013. IAENGGoogle Scholar
  6. 6.
    M. Mendes, M.M. Crisóstomo, A. Paulo Coimbra, Assessing a sparse distributed memory using different encoding methods, in Proceedings of the World Congress on Engineering (WCE), London, UK, July 2009Google Scholar
  7. 7.
    B. Ratitch, D. Precup, Sparse distributed memories for on-line value-based reinforcement learning, in ECML (2004)Google Scholar
  8. 8.
    M. Mendes, A. Paulo Coimbra, M. Crisóstomo, 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, December 2007, pp. 1743–1750Google Scholar
  9. 9.
    S.B. Furber, J. Bainbridge, J.M. Cumpstey, S. Temple, Sparse distributed memory using n-of-m codes. Neural Netw. 17(10), 1437–1451 (2004)CrossRefMATHGoogle Scholar
  10. 10.
    J.D. Keeler, Comparison between Kanerva’s SDM and Hopfield-type neural networks. Cogn. Sci. 12(3), 299–329 (1988)CrossRefGoogle Scholar
  11. 11.
    A.P. Coimbra, M. Mendes, M.M. Crisóstomo, Vision-Based Robot Navigation: Quest for Intelligent Approaches Using a Sparse Distributed Memory (Universal Publishers, Boca Raton, 2012)Google Scholar
  12. 12.
    A. Cardoso-Cachopo, Improving Methods for Single-label Text Categorization. PhD thesis, Universidade Técnica de Lisboa, Oct 2007Google Scholar
  13. 13.
    A. Cardoso-Cachopo, A. Oliveira, Combining LSI with other classifiers to improve accuracy of single-label text categorization, in First European Workshop on Latent Semantic Analysis in Technology Enhanced Learning. EWLSATEL (2007)Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Mateus Mendes
    • 1
    • 2
  • A. Paulo Coimbra
    • 2
  • Manuel M. Crisóstomo
    • 2
  • Jorge Rodrigues
    • 1
    • 2
  1. 1.ESTGOHPolytechnic Institute of CoimbraCoimbraPortugal
  2. 2.Institute of Systems and Robotics, Pólo IIUniversity of CoimbraCoimbraPortugal

Personalised recommendations