Fast Classification Networks For Signal Processing

  title={Fast Classification Networks For Signal Processing},
  author={K. W. Tang and Subhash C. Kak},
We present a generalization of the corner classification approach to training feedforward neural networks that allows rapid learning of nonbinary data. These generalized networks, called fast classification (FC) networks, are compared against backpropagation and radial basis function networks and are shown to have excellent performance for prediction of time series and pattern recognition. FC networks do not require iterative training and they can be used in many signal processing applications… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-10 of 14 references

Instantaneous Learning Neural Networks

  • K. W. Tang
  • Ph.D. dissertation, Louisiina State University…
  • 1999
2 Excerpts

A new corner classification approach to neural network training

  • K. W. Tang, S. Kak
  • Circuits Systems Signal Process., vol. 17, pp…
  • 1998
2 Excerpts

Dynamic radius allocation in corner classification neural networks

  • G. A. Souza, S. Kak
  • Proceedings of the Third International Conference…
  • 1998
1 Excerpt

Fuzzy Neural Systems

  • C. T. Lin, C.S.G. Lee
  • Prentice-Hall, Upper Saddle River, NJ
  • 1996
1 Excerpt