This Article 
 Bibliographic References 
 Add to: 
Neural Networks and Knowledge Engineering
June 1991 (vol. 3 no. 2)
pp. 185-192

A brief overview is given of the nature of present day artificial neural net computing and the authors emphasize the theme that in this mode of computing, knowledge is not represented symbolically, but in the form of distributed processing and localized decision rules. The authors propose that in neural-net computing, the processing is the representation. In other words, the very nature of the processing encodes the knowledge. There is no place and no need for a separate body of global rules to be used by the network for inferencing. If rules exist at all, they are in the nature of local processing steps carried out at individual processors in response to stimuli from other neurons. The authors develop this theme together with a theme which is closely related to it. The second notion is that neural networks may also be thought of and implemented in terms of heterogeneous networks, rather than always or only in terms of massive arrays of identical elemental processors.

[1] D.E. Rumelhart and D. McClelland, eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1-2, MIT Press, Cambridge, Mass., 1986.
[2] Defense Advanced Projects Agency,Neural Network Society. Fairfax, VA: AFCEA International Press, 1988.
[3] Y. H. Pao,Adaptive Pattern Recognition and Neutral Networks, Reading, MA: Addison-Wesley, 1989.
[4] M. Caudill, "Neural networks primer," Parts I-VII,AI Expert, 12/87-5/89.
[5] Y. H. Pao and R. Beer, "The Functional-Link net: A unifying network architecture incorporating higher order Effects," inProc. Int. Neural Network Soc. First Annu. Meet., Boston, MA, Sept. 6-10, 1988.
[6] R.O. Duda and P.E. Hart,Pattern Classification and Scene AnalysisNew York: Wiley, 1973.
[7] C. H. Chen,Statistical Pattern Recognition Washington, DC: Hayden, 1973.
[8] G. A. Carpenter and S. Grossberg, "Category learning and adaptive pattern recognition, a neural network model," inProc. Third Army Conf. Appl. Math. Comput., ARO Rep. 86-1, 1985, pp. 37-56.
[9] Y. H. Pao, "Functional-Link nets: Removing hidden layers,"AI Expert, vol. 4, no. 4, pp. 60-68, 1989.
[10] M.S. Klassen, "Characteristics of functional link net and its use in character recognition," Ph.D. dissertation, Case Western Reserve Univ., Cleveland, OH, 1989.
[11] T. Kohonen, "An introduction to neural computing,"Neural Nerworks, vol. 1, pp. 3-16, 1988.
[12] T. Kohonen, "Learning vector quantization for pattern recognition," Tech. Rep. TKK-F-A601, Helsinki Univ. of Technology.
[13] D. C. Shei and Y. H. Pao, "An extension of the Kohonen LVQ supervised clustering procedure," Tech. Rep. 108-90, Case Western Reserve Univ., Center for Automat. and Intell. Syst. Res., 1990.
[14] R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, "The capacity of the Hopfield associative memory,"IEEE Trans. Inform. Theory, vol. IT-33, pp. 461-482, 1987.
[15] Y. H. Pao and D. J. Sobajic, "Metric synthesis and concept discovery with connectionist networks," inProc. IEEE Syst., Man, Cybern. Conf., vol. 1, Alexandria, VA, pp. 390-395.
[16] D. Harel,Algorithmics: The Spirit of Computing, Addison-Wesley, Reading, Mass., 1987.
[17] J. J. Hopfield and D. W. Tank, "Neural computation of decisions in optimization problems."Biolog. Cybern., vol. 52, pp. 144-152, 1985.
[18] R. Beer, "Intelligence as adaptive behavior: An experiment in computational neuroethology," Ph.D. dissertation, Case Western Univ., Cleveland OH, 1989.

Index Terms:
knowledge engineering; artificial neural net computing; distributed processing; localized decision rules; global rules; local processing steps; neurons; heterogeneous networks; identical elemental processors; distributed processing; knowledge engineering; neural nets
Y.-H. Pao, D.J. Sobajic, "Neural Networks and Knowledge Engineering," IEEE Transactions on Knowledge and Data Engineering, vol. 3, no. 2, pp. 185-192, June 1991, doi:10.1109/69.87998
Usage of this product signifies your acceptance of the Terms of Use.