Rethinking Sigma’s Graphical Architecture: An Extension to Neural Networks

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9782)


The status of Sigma’s grounding in graphical models is challenged by the ways in which their semantics has been violated while incorporating rule-based reasoning into them. This has led to a rethinking of what goes on in its graphical architecture, with results that include a straightforward extension to feedforward neural networks (although not yet with learning).


Cognitive architecture Graphical models Neural network 



This effort has been sponsored by the U.S. Army. Statements and opinions expressed do not necessarily reflect the position or the policy of the United States Government, and no official endorsement should be inferred. We would also like to thank Himanshu Joshi for useful discussions on neural networks in Sigma.


  1. 1.
    Rosenbloom, P.S.: The Sigma cognitive architecture and system. AISB Q. 136, 4–13 (2013)Google Scholar
  2. 2.
    Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)MATHGoogle Scholar
  3. 3.
    Kschischang, F.R., Frey, B.J., Loeliger, H.: Factor graphs and the sum-product algorithm. IEEE Trans. Inf. Theor. 47, 498–519 (2001)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Rumelhart, D.E., McClelland, J.L., The PDP Research Group: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Foundation, vol. 1. MIT Press, Cambridge (1986)Google Scholar
  5. 5.
    Jordan, M.I., Sejnowski, T.J.: Graphical Models: Foundations of Neural Computation. MIT Press, Cambridge (2001)MATHGoogle Scholar
  6. 6.
    Joshi, H., Rosenbloom, P.S., Ustun, V.: Isolated word recognition in the Sigma cognitive architecture. Biologically Inspired Cogn. Architectures 10, 1–9 (2014)CrossRefGoogle Scholar
  7. 7.
    Ustun, V., Rosenbloom, P.S., Sagae, K., Demski, A.: Distributed vector representations of words in the Sigma cognitive architecture. In: Goertzel, B., Orseau, L., Snaider, J. (eds.) AGI 2014. LNCS, vol. 8598, pp. 196–207. Springer, Heidelberg (2014)Google Scholar
  8. 8.
    Rosenbloom, P.S.: Mental imagery in a graphical cognitive architecture. In: Second International Conference on Biologically Inspired Cognitive Architectures (2011)Google Scholar
  9. 9.
    Rosenbloom, P.S.: Combining procedural and declarative knowledge in a graphical architecture. In: 10th International Conference on Cognitive Modeling (2010)Google Scholar
  10. 10.
    Singla, P., Domingos, P.: Lifted first-order belief propagation. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence (2008)Google Scholar
  11. 11.
    Kersting, K., Ahmadi, B., Natarajan, S.: Counting belief propagation. In: Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (2009)Google Scholar
  12. 12.
    Pynadath, D.V., Rosenbloom, P.S., Marsella, S.C., Li, L.: Modeling two-player games in the Sigma graphical cognitive architecture. In: Kühnberger, K.-U., Rudolph, S., Wang, P. (eds.) AGI 2013. LNCS, vol. 7999, pp. 98–108. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  13. 13.
    Milnes, B.G., Pelton, G., Doorenbos, R., Hucka, M., Laird, J., Rosenbloom, P., Newell, A.: A Specification of the Soar Cognitive Architecture in Z. CMU CS Technical report, Pittsburgh (1992)Google Scholar
  14. 14.
    Rosenbloom, P.S., Demski, A., Han, T., Ustun, V.: Learning via gradient descent in Sigma. In: Proceedings of the 12th International Conference on Cognitive Modeling (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Paul S. Rosenbloom
    • 1
    • 2
  • Abram Demski
    • 1
    • 2
  • Volkan Ustun
    • 1
  1. 1.Institute for Creative TechnologiesUniversity of Southern CaliforniaLos AngelesUSA
  2. 2.Department of Computer ScienceUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations