SHRUTI: A neurally plausible model of memory and reasoning:

Foundational paper

  • From simple associations to systematic reasoning, L. Shastri, V. Ajjanagadde. Behavioral and Brain Sciences, Vol. 16, No. 3, 417--494, 1993. (text | table | figures(1) | figures(2)).

    Some early papers

  • Rules and variables in neural nets, V. Ajjanagadde and L. Shastri, Neural Computation. 3, 121--134, 1991.

  • Reflexive Reasoning with Multiple-Instantiation in in a Connectionist Reasoning System with a Typed Hierarchy, D.R. Mani, and L. Shastri. Connection Science, Vol. 5, No. 3 & 4, 205--242. 1993.

    Papers describing some significant additions to the Shruti model

  • A Connectionist Treatment of Negation and Inconsistency, L. Shastri and D.J. Grannes. Proceedings of the Eighteenth Conference of the Cognitive Science Society, 1996. pdf

  • Advances in Shruti --- A neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony, L. Shastri, Applied Intelligence., 11, 79-108 (1999). postscript pdf

  • Seeking coherent explanations --- a fusion of structured connectionism, temporal synchrony, and evidential reasoning. L. Shastri and C. Wendelken, Proceedings of Cognitive Science 2000, Philadelphia, PA, August 2000. postscript pdf

  • Types and Quantifiers in Shruti --- a connectionist model of rapid reasoning and relational processing, L. Shastri. In Hybrid Neural Symbolic Integration, S. Wermter and R. Sun (Eds.), Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence Springer-Verlag, Berlin. (2000). pdf

  • Combining belief and utility in a structured connectionist agent architecture. C. Wendelken and L. Shastri, Proceedings of Cognitive Science 2002, Fairfax, VA, August 2002. pdf

  • A connectionist model of planning via back-chaining search. M. Garagnani, C. Wendelken and L. Shastri, Proceedings of Cognitive Science 2002, Fairfax, VA, August 2002. pdf

  • Acquisition of concepts and causal rules in SHRUTI. C. Wendelken and L. Shastri, Proceedings of Cognitive Science 2003, Boston, MA, August 2003. pdf

  • A Connectionist Encoding of Parameterized Schemas and Reactive Plans, L. Shastri, D. Grannes, S. Narayanan and J. Feldman. To appear in Hybrid Information Processing in Adaptive Autonomous vehicles, G.K. Kraetzschmar and G. Palm (Eds.), Springer-Verlag, Berlin. (Also TR-02-008) pdf

    Other papers in reverse chronological order

  • Comparing the Neural Blackboard and the temporal synchrony based SHRUTI architectures L. Shastri, Behavioral and Brain Sciences, Vol. 29, No. 1, 84--86, 2006. html

  • Multiple instantiation and rule mediation in SHRUTI C. Wendelken and L. Shastri, Connection Science, 16: 211-217, 2004. (final draft, MS Word)

  • Connectionist Mechanisms for Cognitive Control. C. Wendelken and L. Shastri, Neurocomputing, Presented at the 13th Annual Computational Neuroscience Meeting, Baltimore, MD. July 2004. pdf

  • Probabilistic inference and learning in a connectionist causal network. C. Wendelken and L. Shastri. Proceedings of the Second International Symposium on Neural Computation Berlin, Germany, May 2000. pdf

  • An Extended Local Connectionist Manifesto: Embracing Relational and Procedural Knowledge L. Shastri Behavioral and Brain Sciences, To Appear postscript pdf

  • Soft Computing in Shruti --- A neurally plausible model of reflexive reasoning and relational information processing, L. Shastri and C. Wendelken. Proceedings of the Third International Symposium on Soft Computing, 741-747, June 1999, Genova, Italy. postscript

  • Temporal Synchrony, Dynamic Bindings, and SHRUTI -- a representational but non-classical model of reflexive reasoning Behavioral and Brain Sciences Vol. 19, No. 2, 331--337.
    How does a solution of the dynamic binding problem using "signatures" (Lange and Dyer) compare to a solution based on temporal synchrony?

  • A Computational Model of Tractable Reasoning -- Taking Inspiration from Cognition, L. Shastri, Proceedings of IJCAI-93, the Thirteenth International Joint Conference on Artificial Intelligence. France, August-September 1993. pp. 202-207.
    Argues for a strong notion of tractability and identifies a class of reasoning that is tractable in this stronger sense. Motivated by the shruti model.

  • Massively Parallel Knowledge Representation and Reasoning -- Taking a Cue from the Brain, Lokendra Shastri and D.R. Mani. In Parallel Processing for Artificial Intelligence 3, (Eds.) Geller, J., Kitano, H. and Suttner, C. Elsevier Science. 1997.

  • Exploiting temporal binding to learn relational rules within a connectionist network Lokendra Shastri. ICSI TR-97-003.

  • Dealing With Negated Knowledge and Inconsistency in a Neurally Motivated Model of Memory and Reflexive Reasoning Lokendra Shastri and Dean J. Grannes. ICSI TR-95-041.

  • A case study of SHRUTI in Noetica: Open Forum, Volume 2, Issue 7, 1996. Lokendra Shastri and Dean .J. Grannes.