Skip to main content
SpringerLink
Log in

Advances in SHRUTI—A Neurally Motivated Model of Relational Knowledge Representation and Rapid Inference Using Temporal Synchrony

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency—as though these inferences are a reflex response of our cognitive apparatus. This remarkable human ability poses a challenge for cognitive science and computational neuroscience: How can a network of slow neuron-like elements represent a large body of systematic knowledge and perform a wide range of inferences with such speed? The connectionist model SHRUTI attempts to address this challenge by demonstrating how a neurally plausible network can encode a large body of semantic and episodic facts, systematic rules, and knowledge about entities and types, and yet perform a wide range of explanatory and predictive inferences within a few hundred milliseconds. Relational structures (frames, schemas) are represented in SHRUTI by clusters of cells, and inference in SHRUTI corresponds to a transient propagation of rhythmic activity over such cell-clusters wherein dynamic bindings are represented by the synchronous firing of appropriate cells. SHRUTI encodes mappings across relational structures using high-efficacy links that enable the propagation of rhythmic activity, and it encodes items in long-term memory as coincidence and coincidence-error detector circuits that become active in response to the occurrence (or non-occurrence) of appropriate coincidences in the on going flux of rhythmic activity. Finally, “understanding” in SHRUTI corresponds to reverberant and coherent activity along closed loops of neural circuitry. Over the past several years, SHRUTI has undergone several enhancements that have augmented its expressiveness and inferential power. This paper describes some of these extensions that enable SHRUTI to (i) deal with negation and inconsistent beliefs, (ii) encode evidential rules and facts, (iii) perform inferences requiring the dynamic instantiation of entities, and (iv) seek coherent explanations of observations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. L. Shastri, “A computational model of tractable reasoning—Taking inspiration from cognition,” in Proceedings of IJCAI-93, the Thirteenth International Joint Conference on Artificial Intelligence, France, 1993, pp. 202-207.

  2. V. Ajjanagadde and L. Shastri, “Efficient inference with multi-place predicates and variables in a connectionist,” in Proceedings of the Eleventh Conference of the Cognitive Science Society, Ann-Arbor, MI, 1989, pp. 396-403.

  3. V. Ajjanagadde and L. Shastri, “Rules and variables in neural nets,” Neural Computation, vol. 3, pp. 121-134, 1991.

    Google Scholar 

  4. V. Ajjanagadde, “Reasoning with function symbols in a connectionist network,” in Proceedings of the Twelfth Conference of the Cognitive Science Society, Cambridge, MA, 1990, pp. 285-292.

  5. L. Shastri and V. Ajjanagadde, “An optimally efficient limited inference system,” in Proceedings of AAAI-90, Boston, MA, 1990, pp. 563-570.

  6. L. Shastri and V.G. Ajjanagadde, “A connectionist representation of rules, variables and dynamic bindings,” Technical Report MS-CIS-90-05, Department of Computer and Information Science, University of Pennsylvania, 1990.

  7. L. Shastri and V. Ajjanagadde, “From simple associations to systematic reasoning: A connectionist encoding of rules, variables and dynamic bindings using temporal synchrony,” Behavioral and Brain Sciences, vol. 16,no. 3, pp. 417-494, 1993.

    Google Scholar 

  8. L. Shastri, “Neurally motivated constraints on the working memory capacity of a production system for parallel processing,” in Proceedings of the Fourteenth Conference of the Cognitive Science Society, Bloomington, IN, 1992, pp. 159-164.

  9. D.R. Mani and L. Shastri, “Reflexive reasoning with multiple-instantiation in a connectionist reasoning system with a typed hierarchy,” Connection Science, vol. 5,nos. 3/4, pp. 205-242, 1993.

    Google Scholar 

  10. D.R. Mani, “The design and implementation of massively parallel knowledge representation and reasoning systems: A connectionist approach,” Ph.D. Dissertation, Department of Computer and Information Science, University of Pennsylvania, 1995.

  11. P. Milner, “A model for visual shape recognition,” Psychological Review, vol. 81, pp. 521-535, 1974.

    Google Scholar 

  12. C. von der Malsburg, “The correlation theory of brain function,” Internal Report 81-2, Department of Neurobiology, Max-Planck Institute for Biophysical Chemistry, Gottingen, Germany, 1981.

    Google Scholar 

  13. T.J. Sejnowski, “Skeleton filters in the brain,” in Parallel Models of Associative Memory, edited by G.E. Hinton and J.A. Anderson, Erlbaum, 1981.

  14. M. Abeles, Local Cortical Circuits: Studies of Brain Function, Springer Verlag, vol. 6, 1982.

  15. F. Crick, “Function of the thalamic reticular complex: The searchlight hypothesis,” in Proceedings of the National Academy of Sciences, 1984, vol. 81, pp. 4586-4590.

    Google Scholar 

  16. A.R. Damasio, “The brain binds entities and events by multi-regional activation from convergence zones,” Neural Computation, vol. 1, pp. 123-132, 1989.

    Google Scholar 

  17. R. Eckhorn, R. Bauer, W.B. Jordan, W. Kruse, M. Munk, and H.J. Reitbock, “Coherent oscillations: A mechanism for feature linking in the visual cortex? Multiple electrode and correlation analysis in the cat,” Biological Cybernetics, vol. 60, pp. 121-130, 1988.

    Google Scholar 

  18. C.M. Gray, P. Konig, A.K. Engel, and W. Singer, “Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties,” Nature, vol. 338, pp. 334-337, 1989.

    Google Scholar 

  19. V.N. Murthy and E.E. Fetz, “Coherent 25 to 35 Hz oscillations in the sensorimotor cortex of awake behaving monkeys,” in Proceedings of the National Academy of Sciences, USA, 1992, vol. 89, pp. 5670-5674.

    Google Scholar 

  20. M. Abeles, H. Bergman, E. Margalit, and E. Vaadia, “Spatiotemporal firing patterns in the frontal cortex of behaving monkeys,” Journal of Neurophysiology, vol. 70,no. 4, pp. 1629-1638, 1993.

    Google Scholar 

  21. W. Singer, “Synchronization of cortical activity and its putative role in information processing and learning,” Annual Review of Physiology, vol. 55, pp. 349-374, 1993.

    Google Scholar 

  22. W. Singer and C.M. Gray, “Visual feature integration and the temporal correlation hypothesis,” Annual Review of Neuroscience, vol. 18, pp. 555-586, 1995.

    Google Scholar 

  23. C. deCharms, and M. Merzenich, “Primary cortical representation of sounds by the coordination of action-potential timing,” Nature, vol. 381, pp. 610-613, 1996.

    Google Scholar 

  24. M. Usher and N. Donnelly, “Visual synchrony affects binding and segmentation in perception,” Nature, vol. 394, pp. 179-182, 1998.

    Google Scholar 

  25. N.S. Park, D. Robertson, and K. Stenning, “An extension of the temporal synchrony approach to dynamic variable binding in a connectionist inference system,” Knowledge-Based Systems, vol. 8,no. 6, pp. 345-358, 1995.

    Google Scholar 

  26. J. Sougne, “A connectionist model of reflective reasoning using temporal properties of nodes firing,” in Proceedings of the Eighteen Conference of the Cognitive Science Society, Lawrence Erlbaum Associates: San Diego, 1996.

    Google Scholar 

  27. R. Hayward and J. Diederich, “Realising explanation based generalisation,” in Connectionist Systems for Knowledge Representation and Deduction, edited by F. Maire, R. Hayward, and J. Diederich, Queensland University of Technology, Neurocomputing Research Center, 1997.

  28. J.E. Hummel and K.J. Holyoak, “Distributed representations of structure: A theory of analogical access and mapping,” Psychological Review, vol. 104, pp. 427-466, 1997.

    Google Scholar 

  29. L. Shastri and D.J. Grannes, “A connectionist treatment of negation and inconsistency,” in Proceedings of the Eighteenth Conference of the Cognitive Science Society, San Diego, CA, 1996.

  30. L. Shastri, D.J. Grannes, S. Narayanan, and J.A. Feldman, “A connectionist encoding of schemas and reactive plans,” to appear in Hybrid Information Processing in Adaptive Autonomous Vehicles, edited by G.K. Kraetzschmar and G. Palm, Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence, Springer-Verlag: Berlin, 1999.

    Google Scholar 

  31. V. Ajjanagadde, “Abductive reasoning in connectionist networks: Incorporating variables, background knowledge, and structured explanada,” Technical Report WSI 91-6, Wilhelm-Schickard Institute, University of Tubingen, Tubingen, Germany, 1991.

    Google Scholar 

  32. V. Ajjanagadde, “Incorporating background knowledge and structured explanada in abductive reasoning: A framework,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, pp. 650-654, 1993.

    Google Scholar 

  33. V. Ajjanagadde, “Rule-based reasoning in connectionist networks,” Ph.D. Dissertation, Department of Computer Science, University of Minnesota, 1997.

  34. J.E. Lisman and M.A.P. Idiart, “Storage of 7±2 short-term memories in oscillatory subcycles,” Science, vol. 267, pp. 1512-1515, 1995.

    Google Scholar 

  35. O. Jensen and J.E. Lisman, “Novel lists of 7±2 known items can be reliably stored in an oscillatory short-term memory network: Interaction with long term memory,” Learning and Memory, vol. 3, pp. 257-263, 1996.

    Google Scholar 

  36. S.J. Luck and E.K. Vogel, “The capacity of visual working memory for features and conjunctions,” Nature, vol. 390, pp. 279-281, 1997.

    Google Scholar 

  37. J. Henderson, “Connectionist syntactic parsing using temporal variable binding,” Journal of Psycholinguistic Research, vol. 23,no. 5, pp. 353-379.

  38. D. Bailey, N. Chang, J. Feldman, and S. Narayanan, “Extending embodied lexical development,” in Proceedings of the Twentieth Conference of the Cognitive Science Society, Madison, WI, 1998, pp. 84-89.

  39. M.S. Cohen, J.T. Freeman, and S. Wolf, “Meta-recognition in time stressed decision making: Recognizing, critiquing, and correcting,” Human Factors, vol. 38,no. 2, pp. 206-219, 1996.

    Google Scholar 

  40. G.W. Strong, “Phase logic is biologically relevant logic,” Behavioral and Brain Sciences, vol. 16, pp. 472-473, 1993.

    Google Scholar 

  41. L. Shastri and C. Wendelken, “Soft computing in SHRUTI—A neurally plausible model of reflexive reasoning and relational information processing,” 1998, submitted.

  42. G.W. Cottrell, “A Connectionist Approach to Word Sense Disambiguation,” Morgan Kaufmann/Pitman, 1989.

  43. G.W. Cottrell, “From symbols to neurons: Are we yet there?” Behavioral and Brain Science, vol. 16,no. 3, p. 454, 1993.

    Google Scholar 

  44. L. Shastri, “A model of rapid memory formation in the hippocampal system,” in Proceedings of the Nineteenth Annual Conference of the Cognitive Science Society, Stanford University, CA, August 1997, pp. 680-685.

  45. L. Shastri, “Recruitment of binding and binding-error detector circuits via long term potentiation,” Neurocomputing (in press), 1999.

  46. L. Shastri, “Types and quantifiers in Shruti—a connectionist model of rapid reasoning and relational processing,” to appear in Hybrid Neural Symbolic Integration, edited by S. Wermter and R. Sun, Lecture Notes in Computer Science, Lecture Notes in Artificial Intelligence, Springer-Verlag: Berlin, 1999.

    Google Scholar 

  47. E. Tulving, Elements of Episodic Memory, Oxford University Press, 1983.

  48. R.C. O'Keefe and L. Nadel, The Hippocampus as a Cognitive Map, Oxford University Press: London, 1978.

    Google Scholar 

  49. W.J. Freeman, “Deconstruction of neural data yields biologically implausible periodic oscillation,” Behavioral and Brain Sciences, vol. 16,no. 3, pp. 458-459, 1993.

    Google Scholar 

  50. J. Sougne, “Connectionism and the problem of multiple-instantiation,” Trends in Cognitive Sciences, vol. 2, pp. 183-189, 1998.

    Google Scholar 

  51. M.A. Just and P.A. Carpenter, “A capacity theory of comprehension: individual differences in working memory,” Psychological Review, vol. 99,no. 1, pp. 122-149, 1992.

    Google Scholar 

  52. C.M. Gray, A.K. Engel, p. Koenig, and W. Singer, “Properties of synchronous oscillatory neuronal interactions in cat striate cortex,” in Nonlinear Dynamics and Neural Networks, edited by H.G. Schuster and W. Singer, VSH Publishers: Weinheim.

  53. G.A. Miller, “The magical number seven, plus or minus two: Some limits on our capacity for processing information,” Psychological Review, vol. 63, pp. 81-97, 1956.

    Google Scholar 

  54. D. Horn and M. Usher, “Parallel activation of memories in an oscillatory neural network,” Neural Computation, vol. 3, pp. 31-43, 1991.

    Google Scholar 

  55. A. Baddeley, Working Memory, Clarendon Press, 1986.

  56. J. Duncan, S. Martens, and R. Ward, “Restricted attentional capacity within but not between sensory modalities,” Nature, vol. 387, pp. 808-810, 1997.

    Google Scholar 

  57. A. Newell, Unified Theories of Cognition, Harvard University Press, 1990.

  58. L. Shastri and D.R. Mani, “Massively parallel knowledge representation and reasoning: Taking a cue from the brain,” in Parallel Processing for Artificial Intelligence 3, edited by J. Geller, H. Kitano, and C. Suttner, Elsevier Science, 1997.

  59. L. Shastri, “Exploiting temporal binding to learn relational rules within a connectionist network,” TR-97-003, International Computer Science Institute, Berkeley, May 1997.

    Google Scholar 

  60. C. Goller and A. Küchler, “Learning task-dependent distributed representations by backpropagation through Structure,” in Proceedings of the International Conference on Neural Networks, IEEE Press, June 1996, pp. 347-352.

  61. P. Frasconi, M. Gori, and A. Sperduti, “A general framework for adaptive processing of data structures,” IEEE Transactions on Neural Networks, vol. 9,no. 5, pp. 768-786, September 1998.

    Google Scholar 

  62. J. Pollack, “Recursive distributed representations,” Artificial Intelligence, vol. 46,no. 1, pp. 77-105, 1990.

    Google Scholar 

  63. T. Regier, The Human Semantic Potential: Spatial Language and Constrained Connectionism, MIT Press: Cambridge, MA, 1996.

    Google Scholar 

  64. M. Gasser and E. Colunga, “Where do relations come from?” Indiana University Cognitive Science Program, Technical Report 221, January 1998.

  65. G. McKoon and R. Ratcliff, “The comprehension processes and memory structures involved in anaphoric reference,” Journal of Verbal Learning and Verbal Behavior, vol. 19, pp. 668-682, 1980.

    Google Scholar 

  66. G. McKoon and R. Ratcliff, “The comprehension processes and memory structures involved in instrumental inference,” Journal of Verbal Learning and Verbal Behavior, vol. 20, pp. 671-682, 1981.

    Google Scholar 

  67. J.M. Keenan, S.D. Baillet, and P. Brown, “The effects of causal cohesion on comprehension and memory,” Journal of Verbal Learning and Verbal Behavior, vol. 23, pp. 115-126, 1984.

    Google Scholar 

  68. W. Kintsch, “The role of knowledge discourse comprehension: A construction-integration model,” Psychological Review, vol. 95, pp. 163-182, 1988.

    Google Scholar 

  69. G.R. Potts, J.M. Keenan, and J.M. Golding, “Assessing the occurrence of elaborative inferences: Lexical decision versus naming,” Journal of Memory and Language, vol. 27, pp. 399-415, 1988.

    Google Scholar 

  70. J.A. Feldman and D.H. Ballard, “Connectionist models and their properties,” Cognitive Science, vol. 6,no. 3, pp. 205-254, 1982.

    Google Scholar 

  71. J.A. Feldman, “Neural representation of conceptual knowledge,” in Neural Connections, Mental Computation, edited by L. Nadel, L.A. Cooper, P. Culicover, and R.M. Harnish, MIT Press, 1989.

  72. L. Shastri, “Structured connectionist model,” in The Handbook of Brain Theory and Neural Networks, edited by M. Arbib, MIT Press, 1995.

  73. T.E. Lange and M.G. Dyer, “High-level inferencing in a connectionist network,” Connection Science, vol. 1,no. 2, pp. 181-217, 1989.

    Google Scholar 

  74. P. Smolensky, “Tensor product variable binding and the representation of symbolic structure in connectionist systems,” Artificial Intelligence, vol. 46,nos. 1/2, pp. 159-216, 1990.

    Google Scholar 

  75. S. Hölldobler, “CHCL: A connectionist inference system for horn logic based on the connection method and using limited resources,” TR-90-042, International Computer Science Institute, Berkeley, CA, 1990.

    Google Scholar 

  76. J. Barnden and K. Srinivas, “Encoding techniques for complex information structures in connectionist systems,” Connection Science, vol. 3,no. 3, pp. 269-315, 1991.

    Google Scholar 

  77. R. Sun, “On variable binding in connectionist networks,” Connection Science, vol. 4,no. 2, pp. 93-124, 1992.

    Google Scholar 

  78. L. Shastri, “Temporal synchrony, dynamic bindings, and shruti: A representational but non-classical model of reflexive reasoning,” Behavioral and Brain Sciences, vol. 19,no. 2, pp. 331-337, 1996.

    Google Scholar 

  79. G.W. Strong and B.A. Whitehead, “A solution to the tag-assignment problem for neural nets,” Behavioral and Brain Sciences, vol. 12, pp. 381-433, 1989.

    Google Scholar 

  80. D. Wang, J. Buhmann, and C. von der Malsburg, “Pattern segmentation in associative memory,” Neural Computation, vol. 2, pp. 94-106, 1990.

    Google Scholar 

  81. S. Grossberg and D. Somers, “Synchronized oscillations for binding spatially distributed feature codes into coherent spatial patterns,” in Neural Networks for Vision and Image Processing, edited by G. Carpenter and S. Grossberg, MIT Press, 1992.

  82. J.E. Hummel and I. Biederman, “Dynamic binding in a neural network for shape recognition,” Psychological Review, vol. 99, pp. 480-517, 1992.

    Google Scholar 

  83. E. Niebur and C. Koch, “A model for the neuronal implementation of selective visual attention based on temporal correlation among neurons,” Journal of Computational Neuroscience, vol. 1, pp. 141-158, 1994.

    Google Scholar 

  84. E. Bienenstock, “A model of neocortex,” Network: Computation in Neural Systems, vol. 6, pp. 179-224, 1995.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. International Computer Science Institute, 1947 Center Street, Suite 600, Berkeley, CA, 94704. www.icsi.berkeley.edu/∼shastri

    Lokendra Shastri

Authors
  1. Lokendra Shastri
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Shastri, L. Advances in SHRUTI—A Neurally Motivated Model of Relational Knowledge Representation and Rapid Inference Using Temporal Synchrony. Applied Intelligence 11, 79–108 (1999). https://doi.org/10.1023/A:1008380614985

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008380614985

Search

Navigation