Temporal Winner-Take-All Networks: A Time-Based Mechanism for Fast Selection in Neural Networks

IEEE Transactions on Neural Networks

Volumn 4, Issue 5, 1993, Pages 844-853

  Barnden, John A ^a   Srinivas, Kankanahalli ^b  

^a NEW MEXICO STATE UNIVERSITY   (United States)

^b WEST VIRGINIA UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; MATHEMATICAL MODELS; NUMERICAL ANALYSIS; PATTERN RECOGNITION; PROBABILITY;

TEMPORAL WINNER TAKE ALL METHOD; WINNER TAKE ALL NETWORKS;

NEURAL NETWORKS;

EID: 0027662339     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.248461     Document Type: Article

References (35)

1. N. Abramson, “The ALOHA system—another alternative for computer communications,” in Proc. Fall Joint Comput. Conf., 1970, pp. 281–285.
2. S. Ahmad and S. Omohundro, “Equilateral triangles: A challenge for connectionist vision,” in Proc. 12th Annu. Conf. Cognitive Sci. Soc., 1990, pp. 629–636.
3. J. A. Barnden, “Conposit, a neural net system for high-level symbolic processing: Overview of research and description of register-machine level,” memo. Comput. Cognitive Sci., MCCS-88-145, Computing Res. Lab., New Mexico State Univ., Las Cruces, NM, 1988.
4. J. A. Barnden, “Neural-net implementation of complex symbol-processing in a mental model approach to syllogistic reasoning,” in Proc. Eleventh Int. Conf Artificial Intell., Detroit, MI, Aug. 1989, pp. 568–573.
5. J. A. Barnden, “Encoding complex symbolic data structures with some unusual connectionist techniques,” in J. A. Barnden & J. B. Pollack, Eds. Advances in Connectionist and Neural Computation Theory, vol. 1, High-Level Connectionist Models, Norwood, NJ: Ablex.
6. J. A. Barnden, K. Srinivas, and D. Dharmavaratha, “Winner-take-all mechanisms: Time-based versus activation-based mechanisms for selection,” in Proc. IEEE Int. Symp. Circuits Syst., New Orleans, LA, 1990, pp. 215–218.
7. J. A. Barnden and K. Srinivas, “Overcoming rule-based rigidity and connectionist limitations through massively parallel case-based reasoning,” Int. J. Man-Machine Studies, 1992.
8. D. Dharmavaratha, “Unit level simulation of temporal-winner-take-all networks: A neural network model for selection,” M.S. thesis, Dep. Comput. Sci., New Mexico State Univ., Las Cruces, 1990.
9. J. Diederich, “Steps towards knowledge-intensive connectionist learning,” in Advances in Connectionist and Neural Computation Theory, vol. 1, High-Level Connectionist Models, J. A. Barnden and J. B. Pollack, Eds. Norwood, NJ: Ablex, 1991.
10. V. Eliashberg, “Neuron layer with reciprocal inhibition as a mechanism for random choice,” in Proc. Int. Conf. Neural Networks (ICNN-88), 1988, pp. 17–25.
11. S. A. Ellias and S. Grossberg, “Pattern formation, contrast control, and oscillations in the short-term memory of shunting on-center off-surround networks,” Biolog. Cybern., vol. 20, pp. 69–98, 1975.
12. J. A. Feldman and D. H. Ballard, “Connectionist models and their properties,” Cogn. Sci., vol. 6, pp. 205–254, 1982.
13. R. Findley, M. DeYong, and C. Fields, “High-speed analog computation via VLSI implementable neural networks,” in Proc. Third Microelectron. Education Conf. Exposition, San Jose, CA, 1990, pp. 113–123.
14. S. Grossberg, “Nonlinear neural networks: Principles, mechanisms, and architectures,” Neural Networks, vol. 1, pp. 17–61, 1988.
15. D. W. Hillis, The Connection Machine. Cambridge, MA: M.I.T. Press, 1985.
16. C. Koch and S. Ullman, “Selecting one among many: A simple network implementing shifts in selective visual attention,” Human Neurobiology, vol. 4, pp. 219–227, 1985.
17. T. Kohonen, Self-Organization and Associative Memory. Berlin: Springer-Verlag, 1984.
18. T. Lange, (1990). Personal Communication.
19. J. Lazzaro, S. Ryckebusch, M. A. Mahowald, and C. A. Mead, “Winner-take-all networks of O(n) complexity,” in In Advances in Neural Information Processing Systems. 1, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989.
20. M. Lemmon and B. V. K. Kumar, “Neural networks as associate memories,” in Proc. IEEE First Int. Conf. Neural Networks, vol. 2, San Diego, CA, 1987, pp. 213–223.
21. R. P. Lippmann, “An Introduction to programming with neural nets,” IEEE ASSP Mag., vol. 4, no. 2, pp. 4–22, 1987.
22. R. P. Lippmann, “Review of neural networks for speech recognition,” Neural Computation, vol. 1, pp. 1–38, 1989.
23. E. Majani, R. Erlanson, and Y. Abu-Mostafa, “On the K-winners-take-all network,” in Advances in Neural Information Processing Systems 1, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989, pp. 634–642.
24. S. Raghuram, personal communication, 1990.
25. J. A. Reggia, “Properties of a competition-based activation mechanism in neuromimetic network models,” in Proc. IEEE First Int. Conf. Neural Networks, vol 2, San Diego, CA, 1987, pp. 213–223.
26. L. Shastri, “A connectionist approach to knowledge representation and limited inference, Cognitive Sci., vol. 12, pp. 331–392, 1988.
27. L. Shastri and V. Ajjanagadde, “A connectionist system for rule based reasoning with multi-place predicates and variables,” MS-CIS-89-06, Dep. Comput. and Inform. Sci., Univ. of Pennsylvania, Philadelphia, PA, 1989.
28. K. Srinivas, “Selection in massively parallel connectionist networks,” Ph.D. dissertation, Comput. Sci. Dep., New Mexico State Univ., Las Cruces, NM, 1991.
29. K. Srinivas and J. A. Barnden, “Competition and selection in neural networks with distributed representations,” in Proc. Fifth Rocky Mountain Conf. Artificial Intell., RMCAI-90, Las Cruces, NM, 1990, pp. 117–121.
30. K. Srinivas and J. A. Barnden, “Temporal winner-take-all networks for arbitrary selection in connectionist and neural networks,” presented at the First. Int. Joint Conf. Neural Networks, Washington, DC.
31. D. S. Touretzky, “Representing and transforming recursive objects in a neural network,” or “Trees do grow on Boltzmann Machines,” in Proc. 1986 IEEE Int. Conf. Syst., Man, Cybern., Atlanta, GA, 1986.
32. D. S. Touretzky and G. E. Hinton, “A distributed connectionist production system,” Cognitive Sci., vol. 12, no. 3, pp. 423–466, 1988.
33. D. S. Touretzky and G. E. Hinton, “Symbols among the neurons: Details of a connectionist inference architecture,” in Proc. Ninth Int. Joint Conf Artificial Intell., 1985, pp. 238–243.
34. S. H. Weber, “Acquiring categorical aspects: A connectionist account of figurative noun semantics,” in Proc. Fifth Rocky Mountain Conf on Al, Las Cruces, NM, 1990, pp. 295–300.
35. A. L. Yuille and Grzywacz, “A winner-take-all mechanism based on presynaptic inhibition feedback,” Neural Comput., vol. 1, pp. 334—347, 1989.