This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Nonbinary Neural Network Design
September 1993 (vol. 42 no. 9)
pp. 1132-1135

In earlier studies a distributed neural network, referred to as a neuromic array, was introduced. The earlier designs were restricted to binary alphabets. The present study loosens this restriction by demonstrating the design extension to the quartic case. A natural morphism between the quartic valued and binary valued vector spaces is used to establish a design equivalence between the two settings. This correspondence compares the robustness and performance of equivalent binary and quartic designs.

[1] E. Gardner, "Multiconnectedneural network models,"J. Phys. A, vol. 20, pp. 3453-3464, 1987.
[2] R. Hecht-Nielson,Neurocomputing. Reading, MA: Addison-Wesley, 1990.
[3] P. Antognetti and V. Milutinovic,Neural Networks, vol. I. Englewood Cliffs, NJ: Prentice-Hall, 1991.
[4] T. Khanna,Foundations of Neural Networks, Reading, MA: Addison-Wesley, 1990.
[5] Y. C. Lee, G. Doolen, H. H. Chen, G. Z. Sun, T. Maxwell, H. Y. Lee, and C. L. Giles, "Machine learning using a higher order correlation network,"Physica, vol. 22D, pp. 276-306, 1986.
[6] W. A. Porter and S. Ligade, "Extending memory in the neuromic array," inProc. IEEE Southeastcon'92, Birmingham, AL, Apr. 1992.
[7] W. A. Porter, "Neuromic arrays: Design and performance," inProc. WNN'91 Workshop Neural Networks, Auburn Univ., Feb. 1991.
[8] D.E. Rumelhart and D. McClelland, eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1-2, MIT Press, Cambridge, Mass., 1986.
[9] W. A. Porter, "Polyarrays as distributive memory recognition functions," inProc. ComCon 88, Baton Rouge, LA, Oct. 19-21, 1988, pp. 723-731.
[10] W. A. Porter and J. L. Aravena, "Generalized distributive memory arrays," inAdvances in Computing and Control. Berlin, Germany: Springer-Verlag, 1989, p. 23.
[11] W. A. Porter and W. Liu, "Object recognition by a massively parallel 2-D neural architecture," to appear inMultidimensional Syst. and Signal Processing.
[12] W. A. Porter, "Using polynomic embedding for neural network design,"IEEE Trans. Circuits, Syst., vol. 39, no. 6, 1992.
[13] W. A. Porter, "Recent advances in neural arrays,"Circuits, Syst., Signal Processing., vol. 12, no. 2, 1993.
[14] D. Prados and S. Kak, "Non-binary neural networks," inAdvances in Computing and Control. Berlin, Germany: Springer-Verlag, 1989, pp. 87.
[15] J. Vemuri, Ed.,Artificial Neural Networks: Theoretical Concepts, vol. 1, Neural Networks Series. Washington, DC: IEEE Comput. Soc., 1988.
[16] P.D. Wasserman,Neural Computing: Theory and Practice, Van Nostrand Reinhold, New York, 1989.
[17] C. A. Mead,Analog VLSI and Neural Systems. Reading, MA: Addison-Wesley, 1989.

Index Terms:
nonbinary; neural network; neuromic array; distributed neural network; quartic case; robustness; performance; binary; neural nets.
Citation:
W.A. Porter, Xiaoyan Zheng, "A Nonbinary Neural Network Design," IEEE Transactions on Computers, vol. 42, no. 9, pp. 1132-1135, Sept. 1993, doi:10.1109/12.241601
Usage of this product signifies your acceptance of the Terms of Use.