Efficient algorithms for function approximation with piecewise linear sigmoidal networks

@article{Hush1998EfficientAF,
  title={Efficient algorithms for function approximation with piecewise linear sigmoidal networks},
  author={Don R. Hush and Bill G. Horne},
  journal={IEEE transactions on neural networks},
  year={1998},
  volume={9 6},
  pages={1129-41}
}
This paper presents a computationally efficient algorithm for function approximation with piecewise linear sigmoidal nodes. A one hidden layer network is constructed one node at a time using the well-known method of fitting the residual. The task of fitting an individual node is accomplished using a new algorithm that searches for the best fit by solving a sequence of quadratic programming problems. This approach offers significant advantages over derivative-based search algorithms (e.g… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

A Piecewise Linear Network Classifier

2007 International Joint Conference on Neural Networks • 2007
View 13 Excerpts
Highly Influenced

A Parameter Inspection Method of Dual-Status Spring Based on Contour Detection and Location

2013 International Conference on Computational and Information Sciences • 2013

A Parts State Correction Device Based on Hough Transform

2012 Fourth International Conference on Computational and Information Sciences • 2012

A Neural Network of Smooth Hinge Functions

IEEE Transactions on Neural Networks • 2010
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 48 references

Learning with piece-wise linear networks

Int. J. Neural Syst. • 1995
View 12 Excerpts
Highly Influenced

Time series Prediction: Forcasting the Fu- ture and Understanding the Past

A. S. Weigend, N. A. Gershenfeld
Santa Fe Institute Studies in the Sciences of Complexity. Addison{Wesley, Redding, MA • 1994
View 4 Excerpts
Highly Influenced

Time series prediction using delay coordinate embedding

T. Sauer
A.S. Weigend and N.A. Gershenfeld, editors, Time series Prediction: Forcasting the Future and Understanding the Past, Santa Fe Institute Studies in the Sciences of Complexity, pages 175{194. Addison{Wesley, Redding, MA • 1994
View 10 Excerpts
Highly Influenced

Universal approximation bounds for superpositions of a sigmoidal function

IEEE Trans. Information Theory • 1993
View 11 Excerpts
Highly Influenced

Function approximation using ramps

L. Breiman, J. H. Friedman
Snowbird Workshop on Machines that Learn • 1994
View 8 Excerpts
Highly Influenced

A note on error bounds for approximation in inner product spaces

A. T. Dingankar, I. W. Sandberg
Circuits, Systems and Signal Processing, 15(4):519{522 • 1996
View 1 Excerpt

Implementing projection pursuit learning

IEEE Trans. Neural Networks • 1996
View 1 Excerpt

Similar Papers

Loading similar papers…