SHRUTI: A Neurally Motivated Architecture for Rapid, Scalable Inference

  • Lokendra Shastri
Part of the Studies in Computational Intelligence book series (SCI, volume 77)

The ability to reason effectively with a large body of knowledge is a cornerstone of human intelligence. Consequently, the development of efficient, largescale reasoning systems has been a central research goal in computer science and artificial intelligence. Although there has been notable progress toward this goal, an efficient, large-scale reasoning system has remained elusive. Given that the human brain is the only extant system capable of supporting a broad range of efficient, large-scale reasoning, it seems reasonable to expect that an understanding of how the brain represents knowledge and performs inferences might lead to critical insights into the structure and design of large-scale inference syste

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Stickel, M., Waldinger, R., Chaudhri, V.: A guide to snark. Technical report, Artificial Intelligence Center, SRI International, Menlo Park CA (2000)Google Scholar
  2. 2.
    Kalman, J.: Automated reasoning with Otter. Rinton Press, Princeton NJ (2001) MATHGoogle Scholar
  3. 3.
    McCune, W.: Otter 3.3 reference manual. Technical Report Technical Memoran-dum No. 263, Mathematical and Computer Science Division, Argonne National Laboratory, Argonne IL (2003)Google Scholar
  4. 4.
    Chalupsky, H., MacGregor, R., Russ, T.: PowerLoom Manual. Information Sciences Institute, Marina del Rey CA. (2006)Google Scholar
  5. 5.
    Carpenter, P., Just, M.: Reading comprehension as eyes see it. In Just, M., Carpenter, P., eds.: Cognitive Processes in Comprehension. Erlbaum, Marwah NJ (1977)Google Scholar
  6. 6.
    McKoon, G., Ratcliff, R.: Inference during reading. Psychological Review 99 (1992) 440-466CrossRefGoogle Scholar
  7. 7.
    Keenan, J., Baillet, S., Brown, P.: The effects of causal cohesion on comprehen-sion and memory. Journal of Verbal Learning and Verbal Behaavior 23 (1984) 115-126CrossRefGoogle Scholar
  8. 8.
    Kintsch, W.: The role of knowledge discourse comprehension: A construction-integration model. Psychological Review 95 (1988) 163-182CrossRefGoogle Scholar
  9. 9.
    Shastri, L., Ajjanagadde, V.: From simple associations to systematic reasoning. Behavioral and Brain Sciences 16 (1993) 417-494Google Scholar
  10. 10.
    Feldman, J.: Dynamic connections in neural networks. Biological Cybernetics 46(1982) 27-39CrossRefGoogle Scholar
  11. 11.
    Smolensky, P.: Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artificial Intelligence 46 (1990) 159-216CrossRefMathSciNetGoogle Scholar
  12. 12.
    Plate, T.: Holographic reduced representations. IEEE Transactions on Neural Networks 6 (1995) 623-641CrossRefGoogle Scholar
  13. 13.
    Touretzky, D., Hinton, G. Cognitive Science 12 (1988) 423-466CrossRefGoogle Scholar
  14. 14.
    Barnden, J.A., Srinivas, K.: Encoding techniques for complex information structures in connectionist systems. Connection Science 3 (1991) 269-315CrossRefGoogle Scholar
  15. 15.
    Lange, T., Dyer, M.: High-level inferencing in a connectionist network. Connection Science 1 (1989) 181-217CrossRefGoogle Scholar
  16. 16.
    Sun, R.: On variable binding in connectionist networks. Connection Science 4 (1992) 93-124CrossRefGoogle Scholar
  17. 17.
    Ajjanagadde, V., Shastri, L.: Efficient inference with multi-place predicates and variables in a connectionist system. In: Proceedings of the Eleventh Conference of the Cognitive Science Society. (1989) 396-403Google Scholar
  18. 18.
    Park, N., Robertson, D., Stenning, K.: An extension of the temporal synchrony approach to dynamic variable binding. Knowledge-Based Systems 8 (1995) 345- 358Google Scholar
  19. 19.
    Sougne, J.: Connectionism and the problem of multiple instantiation. Trends in Cognitive Sciences 2 (1998) 183-189CrossRefGoogle Scholar
  20. 20.
    Hummel, J., Holyoak, K.: Distributed representations of structure: a theory of analogical access and mapping. Psychological Review 104 (1997) 427-466CrossRefGoogle Scholar
  21. 21.
    von der Malsburg, C.: The correlation theory of brain function. Technical Re-port 81-2, Max-Planck Institute for Biophysical Chemistry, Gottingen Germany (1981)Google Scholar
  22. 22.
    Shastri, L.: Temporal synchrony, dynamic bindings, and shruti - a represen-tational but non-classical model of reflexive reasoning. Behavioral and Brain Sciences 19 (1996) 331-337CrossRefGoogle Scholar
  23. 23.
    Shastri, L.: Advances in shruti - a neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony. Applied Intelligence 11 (1999) 79-108CrossRefGoogle Scholar
  24. 24.
    Shastri, L.: Types and quantifiers in shruti — a connectionist model of rapid reasoning and relational processing. In Werter, S., Sun, R., eds.: Hybrid Informa-tion Processing in Adaptive Autonomous Vehicles. Springer-Verlag, Heidelberg Germany (2000) 28-45Google Scholar
  25. 25.
    Mani, D., Shastri, L.: Reflexive reasoning with multiple-instantiation in a con-nectionist reasoning system with a type hierarchy. Connection Science 5 (1993) 205-242CrossRefGoogle Scholar
  26. 26.
    Shastri, L., Wendelken, C.: Seeking coherent explanations - a fusion of struc-tured connectionism, temporal synchrony, and evidential reasoning. In: Pro-ceedings of the Twenty-Second Conference of the Cognitive Science Society, Philadelphia PA (2000)Google Scholar
  27. 27.
    Wendelken, C., Shastri, L.: Probabilistic inference and learning in a connection-ist causal network. In: Proceedings of the Second International Symposium on Neural Computation, Berlin Germany (2000)Google Scholar
  28. 28.
    Wendelken, C., Shastri, L.: Combining belief and utility in a structured con-nectionist agent architecture. In: Proceedings of the Twenty-Fourth Annual Conference of the Cognitive Science Society, Fairfax VA (2002)Google Scholar
  29. 29.
    Shastri, L., Grannes, D.: A connectionist treatment of negation and inconsistency. In: Proceedings of the Eighteenth Conference of the Cognitive Science Society. (1996)Google Scholar
  30. 30.
    Shastri, L., Grannes, D., Narayanan, S., Feldman, J.: A connectionist encoding of parameterized schemas and reactive plans. Technical Report TR-02-008, International Computer Science Institute, Berkeley, California, 94704 (2002)Google Scholar
  31. 31.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Francisco CA (1988)Google Scholar
  32. 32.
    Bellman, R.: Dynamic Programming. Princeton University Press, Princeton NJ (1957)MATHGoogle Scholar
  33. 33.
    Thompson, B., Cohen, M.: Naturalistic decision making and models of compu-tational intelligence. Neural Computing Surveys 2 (1999) 26-28Google Scholar
  34. 34.
    Shastri, L.: Episodic memory trace formation in the hippocampal system: a model of cortico-hippocampal interactions. Technical Report TR-01-004, Inter-national Computer Science Institute, Berkeley, California, 94704 (2001)Google Scholar
  35. 35.
    Shastri, L.: Episodic memory and cortico-hippocampal interactions. Trends in Cognitive Sciences 6 (2002) 162-168CrossRefGoogle Scholar
  36. 36.
    Bliss, T., Collingridge, G.: A synaptic model of memory: long-term potentiation in the hippocampus. Nature 361 (1993) 31-39CrossRefGoogle Scholar
  37. 37.
    Shastri, L.: A computationally efficient abstraction of long-term potentiation. Neurocomputing 44-46 (2002) 33-41CrossRefGoogle Scholar
  38. 38.
    Bi, G., Poo, M.: Synaptic modification by correlated activity: Hebb’s postulate revisited. Annual review of neuroscience 24 (2001) 139-166CrossRefGoogle Scholar
  39. 39.
    Wickelgren, W.A.: Learning and Memory. Prentice Hall, Englewood Cliffs NJ (1977)Google Scholar
  40. 40.
    Sowa, J., ed.: Principles of Semantic Networks. Morgan Kaufmann, San Francisco (1991)MATHGoogle Scholar
  41. 41.
    Jordan, M., ed.: Learning in Graphical Models. MIT Press, Cambridge MA (1998)MATHGoogle Scholar
  42. 42.
    Quillian, M.: Semantic memory. In Minsky, M., ed.: Semantic Information Processing. MIT Press, Cambridge MA (1968) 227-270Google Scholar
  43. 43.
    Fahlman, S.: NETL: A System for Representing and Using Real-World Knowledge. MIT Press, Cambridge MA (1979)MATHGoogle Scholar
  44. 44.
    Charniak, E.: Passing markers: A theory of contextual influence in language comprehension. Cognitive Science 7 (1983) 171-190CrossRefGoogle Scholar
  45. 45.
    Hendler, J.: Integrating marker-passing and problem solving: a spreading acti-vation approach to improved choice in problem solving. Erlbaum, Marwah NJ (1987)Google Scholar
  46. 46.
    Henderson, J.: Connectionist syntactic parsing using temporal variable binding. Journal of Psycholinguistic Research 23 (1994) 353-379CrossRefGoogle Scholar
  47. 47.
    Shastri, L.: A computational model of tractable reasoning - taking inspiration from cognition. In: Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, Chambery France (1993) 202-207Google Scholar
  48. 48.
    Mani, D.: The design and implementation of massively parallel knowledge rep-resentation and reasoning systems: a connectionist approach. PhD thesis, Uni-versity of Pennsylvania (1995)Google Scholar
  49. 49.
    Shastri, L., Mani, D.: Massively parallel knowledge representation and reason-ing: Taking a cue from the brain. In Geller, J., Kitano, H., Suttner, C., eds.: Parallel Processing for Artificial Intelligence 3. Elseveir Science, Amsterdam Netherland (1997) 3-40CrossRefGoogle Scholar
  50. 50.
    McIlraith, S., Amir, E.: Theorem proving with structured theories. In: Proc. of the Seventeenth International Joint Conference on Artificial Intelligence, Seattle WA (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Lokendra Shastri
    • 1
  1. 1.International Computer Science InstituteBerkeleyUSA

Personalised recommendations