Improving the Convergence of Backpropagation by Opposite Transfer Functions

@article{Ventresca2006ImprovingTC,
  title={Improving the Convergence of Backpropagation by Opposite Transfer Functions},
  author={Mario Ventresca and Hamid R. Tizhoosh},
  journal={The 2006 IEEE International Joint Conference on Neural Network Proceedings},
  year={2006},
  pages={4777-4784}
}
The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately learn the task is considerable. Many existing approaches have improved the convergence rate by altering the learning algorithm. We present a simple alternative approach inspired by opposition-based learning that simultaneously considers each network transfer function and its opposite. The effect is an improvement in… CONTINUE READING
Highly Cited
This paper has 139 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 57 citations

140 Citations

01020'09'12'15'18
Citations per Year
Semantic Scholar estimates that this publication has 140 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 15 references

Opposite - Based Reinforcement Learning ”

  • R. Hecht-Nielsen
  • Journal of Advanced Computational Intelligence…
  • 2005

Neural Networks for Modeling and Control of Dynamic Systems: A Practitioner’s Handbook

  • P. M. Norgaard
  • Springer-Verlag New York
  • 2000
1 Excerpt