Neural Network Hybrid Learning: Genetic Algorithms & Levenberg-Marquardt

@inproceedings{Prudncio2003NeuralNH,
  title={Neural Network Hybrid Learning: Genetic Algorithms & Levenberg-Marquardt},
  author={Ricardo B. C. Prud{\^e}ncio and Teresa Bernarda Ludermir},
  year={2003}
}
The success of an Artificial Neural Network (ANN) strongly depends on its training process. Gradient-based techniques have been satisfactorily used in the ANN training. However, in many cases, these algorithms are very slow and susceptible to the local minimum problem. In our work, we implemented a hybrid learning algorithm that integrates Genetic Algorithms(GAs) and the LevenbergMarquardt(LM) algorithm, a second order gradient-based technique. The GA-LM algorithm was used to train a Time-Delay… CONTINUE READING
BETA

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Evolving Multilayer Perceptrons

  • A ETO
  • Neural Processing Letters,
  • 2000
Highly Influential
9 Excerpts

Analysis and Design of the Constructive Neural Networks for Complex Systems Modeling

  • M.J.S. VALENCA
  • Ph.D Thesis (in portuguese),
  • 1999
2 Excerpts

84–91. HANCOCK, P.J.B

  • Algorithms, CA San Mateo
  • 1992

Similar Papers

Loading similar papers…