Skip to main content
SpringerLink
Log in

Auxilliary computations for perceptron networks

  • Published:
Circuits, Systems and Signal Processing Aims and scope Submit manuscript

Abstract

In this study we consider a multilayer perceptron network with sigmoidal activation and trained via the backpropagation algorithm. The output of all neurons is collected and a simple linear regression is performed. It is shown that untrained networks with randomly chosen coefficients perform comparably with fully trained networks. This result casts a new light on the role of activation functions, the impact of dimensionality, and the efficacy of training algorithms such as backpropagation.

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. Amari, S., Characteristics of randomly connected threshold-element networks and networks systems,Proc. IEEE, vol. 59, 1971.

  2. Carpenter, G., et al., Fuzzy ARTMAP,IEEE Trans. Neural Networks, vol. 3, no. 5, Sept. 1992.

  3. Chiang, C. C. and Fu, H. C., A new simplified second-order multilayer perceptron for improving learning speed and generalization capability, private communication.

  4. Lang, K. K., and Witbrock, M. K., Learning to tell two spirals apart,Proc. 1988 Connectionist Models Summer School, pp. 52–61, Morgan Kaufman, 1988.

  5. Porter, W. A., Using polynomial embeddings for neural network design,IEEE Trans. Neural Networks, vol. 39, no. 6, 1992.

    Google Scholar 

  6. Porter, W. A., Recent progress on higher order moment neural arrays,Circuits Systems Signal Process., vol. 12, no. 2, pp. 309–329, 1993.

    Google Scholar 

  7. Porter, W. A., and Liu, W., Object recognition by a massively parallel 2-D neural architecture,Multidimensional Systems and Signal Processing, vol. 5, pp. 179–201, 1994.

    Google Scholar 

  8. Porter, W. A., and Liu, W., On the performance of higher order moment neural computation,Proc. IEEE SoEastCon, Miami, FL, April 1994.

  9. Porter, W., and Liu, W., Neural network training enchantment, to appear,Circuits, Systems, and Signal Processing, 1996.

  10. Porter, W., and Zhang, X., A nonbinary neural network design,IEEE Trans. Comp., vol. 42, no. 9, pp. 1132–1135, Sept. 1993.

    Google Scholar 

  11. Rozonoer, L., Random logic networks I, II, III, inAutomatic Remote Controls, vols. 5–7, 1969.

  12. Wilensky, G., Analysis of neural network issues,DARPA Neural Network Program Review, Oct. 29–30, 1990.

Download references

Author information

Authors and Affiliations

  1. The Laboratory for Advanced Computer Studies, The University of Alabama in Huntsville, 35899, Huntsville, Alabama

    William A. Porter, Wei Liu & Chin-Yi Wu

Authors
  1. William A. Porter
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chin-Yi Wu
    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

Porter, W.A., Liu, W. & Wu, CY. Auxilliary computations for perceptron networks. Circuits Systems and Signal Process 15, 51–69 (1996). https://doi.org/10.1007/BF01187693

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01187693

Keywords

Search

Navigation