Cognitive Computation

, Volume 4, Issue 2, pp 172–180 | Cite as

Extended Sparse Distributed Memory and Sequence Storage

  • Javier SnaiderEmail author
  • Stan Franklin


Sparse distributed memory (SDM) is an auto-associative memory system that stores high-dimensional Boolean vectors. SDM uses the same vector for the data (word) and the location where it is stored (address). Here, we present an extension of the original SDM that uses word vectors of larger size than address vectors. This extension preserves many of the desirable properties of the original SDM: auto-associability, content addressability, distributed storage and robustness over noisy inputs. In addition, it adds new functionality, enabling an efficient auto-associative storage of sequences of vectors, as well as of other data structures such as trees. Simulations testing this new memory are described.


Sparse distributed memory Episodic memory Sequence representation Cognitive modeling 


  1. 1.
    Kanerva P. Sparse distributed memory. Cambridge: The MIT Press; 1988.Google Scholar
  2. 2.
    Baddeley AD, Conway M, Aggleton JP. Episodic memory. Oxford: Oxford University Press; 2001. p. 294.Google Scholar
  3. 3.
    Franklin S, et al. The role of consciousness in memory. Brains Minds Media. 2005;1:1–38.Google Scholar
  4. 4.
    Furber SB, et al. A sparse distributed memory based upon N-of-M codes. Neural Netw. 2004;17(10):1437–51.PubMedCrossRefGoogle Scholar
  5. 5.
    Bose J, Furber SB, Shapiro JL. Spiking neural sparse distributed memory implementation for learning and predicting temporal sequences. Lect Notes Comput Sci. 3696/2005. p. 115–20; 2005.Google Scholar
  6. 6.
    Meng H, et al. A modified sparse distributed memory model for extracting clean patterns from noisy inputs. In International joint conference on neural networks (IJCNN)2009. Atlanta, GA; 2009.Google Scholar
  7. 7.
    Ramamurthy U, D’Mello SK, Franklin S. Realizing forgetting in a modified sparse distributed memory system. In: Schunn C, Lane S. editors. Proceedings of the 28th Annual Conference Of The Cognitive Science Society, Mahwah, NJ: Lawrence Erlbaum Associates; 2006. p. 1992–97.Google Scholar
  8. 8.
    Ramamurthy U, Franklin S. Memory systems for cognitive agents. In Proceedings of human memory for artificial agents symposium at the artificial intelligence and simulation of behavior convention (AISB’11)2011. UK: University of York; 2011. p. 35–40.Google Scholar
  9. 9.
    D’Mello SK, Ramamurthy U, Franklin S. Encoding and retrieval efficiency of episodic data in a modified sparse distributed memory system. In: Proceedings of the 27th annual meeting of the cognitive science society. Stresa, Italy; 2005.Google Scholar
  10. 10.
    Ramamurthy U, D’Mello SK, Franklin S. modified sparse distributed memory as transient episodic memory for cognitive software agents. In: Proceedings of the international conference on systems, man and cybernetics 2004. Piscataway: IEEE; 2004.Google Scholar
  11. 11.
    Snaider J, McCall R, Franklin S. Time production and representation in a conceptual and computational cognitive model. Cogn Syst Res. 2012;13(1):59–71.CrossRefGoogle Scholar
  12. 12.
    Sun R, Giles CL. Sequence learning: from recognition and prediction to sequential decision making. IEEE Intell Syst. 2001;16(4):67–70.CrossRefGoogle Scholar
  13. 13.
    Kurby CA, Zacks JM. Segmentation in the perception and memory of events. Trends Cogn Sci. 2008;12(2):72–9.PubMedCrossRefGoogle Scholar
  14. 14.
    Kanerva P. Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cognit Comput. 2009;1(2):139–59.CrossRefGoogle Scholar
  15. 15.
    Snaider J, Franklin S. Extended sparse distributed memory. In: Biological inspired cognitive architectures 2011. Washington; 2011.Google Scholar
  16. 16.
    Franklin S. Artificial minds. Cambridge: MIT Press; 1995.Google Scholar
  17. 17.
    Ratitch B, Precup D. Sparse distributed memories for on-line value-based reinforcement learning. Lect Notes Comput Sci. 2004;3201:347–58.CrossRefGoogle Scholar
  18. 18.
    Fan KC, Wang YK. A genetic sparse distributed memory approach to the application of handwritten character recognition. Pattern Recogn Lett. 1997;30(12):2015–22.Google Scholar
  19. 19.
    Anwar A, Dasgupta D, Franklin S. Using genetic algorithms for sparse distributed memory initialization. In: International conference genetic and evolutionary computation (GECCO); 1999.Google Scholar
  20. 20.
    Jaeckel LA, An alternative design for a sparse distributed memory. Research Institute for Advanced Computer Science, NASA Ames Research Center; 1989.Google Scholar
  21. 21.
    Jaeckel LA, A class of designs for a sparse distributed memory, Research Institute for Advanced Computer Science, NASA Ames Research Center; 1989.Google Scholar
  22. 22.
    Karlsson R. A fast activation mechanism for the Kanerva SDM memory. In: Proceedings of the RWC symposium. p. 69–0; 1995.Google Scholar
  23. 23.
    Kanerva P. Sparse distributed memory and related models, in associative neural memories: theory and implementation, Hassoun MH, editor. New York: Oxford University Press; 1993. p. 50–76.Google Scholar
  24. 24.
    Chou PA. The capacity of the Kanerva associative memory. IEEE Trans Inf Theory. 1989;35(2):281–98.CrossRefGoogle Scholar
  25. 25.
    Keeler JD. Comparison between Kanerva’s SDM and Hopfield-type neural networks. Cognitive Sci. 1988;12:299–329.CrossRefGoogle Scholar
  26. 26.
    Willshaw DJ. Holography, associative memory, and inductive generalization. In: Hinton GE, Anderson JA, editors. In parallel models of associative memory. Hillsdale: Erlbaum; 1981. p. 83–104.Google Scholar
  27. 27.
    Knoblauch A, Palm G, Sommer FT. Memory capacities for synaptic and structural plasticity. Neural Comput. 2010;22(2):289–341.PubMedCrossRefGoogle Scholar
  28. 28.
    Lawrence M, Trappenberg T, Fine A. Rapid learning and robust recall of long sequences in modular associator networks. Neurocomputing. 2006;69(7–9):634–41.CrossRefGoogle Scholar
  29. 29.
    Wang D, Yuwono B. Incremental learning of complex temporal patterns. IEEE Trans Neural Netw. 1995;7:1465–81.CrossRefGoogle Scholar
  30. 30.
    Stringer SM, et al. Selforganizing continuous attractor networks and motor function. Neural Netw. 2003;16(2):161–82.PubMedCrossRefGoogle Scholar
  31. 31.
    Maurer A, Hersch M, Billard AG. Extended hopfield network for sequence learning: application to gesture recognition. In: Proceedings of the ICANN 2005; 2005.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Computer Science Department and Institute for Intelligent SystemsThe University of MemphisMemphisUSA

Personalised recommendations