Modified Levenberg-Marquardt Method for Neural Networks Training

  title={Modified Levenberg-Marquardt Method for Neural Networks Training},
  author={Mohammad Bagher Tavakoli},
In this paper a modification on Levenberg-Marquardt algorithm for MLP neural network learning is proposed. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. An example is given to show usefulness of this method. Finally a simulation verifies the results of proposed method. Keywords—Levenberg-Marquardt, modification, neural network, variable learning rate. 
Highly Cited
This paper has 107 citations. REVIEW CITATIONS

From This Paper

Figures and tables from this paper.


Publications citing this paper.
Showing 1-10 of 52 extracted citations

Data from past patients used to streamline adjustment of levels for cochlear implant for new patients

2016 IEEE Symposium Series on Computational Intelligence (SSCI) • 2016
View 7 Excerpts
Highly Influenced

Computer-aided predicting of compressive Strength of Concrete Containing Cr 2 O 3 Nanoparticles

Farzad Soleymani, Pouriya Fataei
View 5 Excerpts
Highly Influenced

The role of the Islamic Azad University in science production of Iran: from the past to the future

Neural Computing and Applications • 2012
View 3 Excerpts
Highly Influenced

108 Citations

Citations per Year
Semantic Scholar estimates that this publication has 108 citations based on the available data.

See our FAQ for additional information.


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

Acceleration of back-propagation through learning rate and momentum adaptation

A. A. Miniani, Williams, D R.
Proceedings of International Joint Conference on Neural Networks, San Diego, CA, 1, 676-679, 1990. • 1990

Back-propagation improvements based on heuristic arguments

T Samad
Proceedings of International Joint Conference on Neural Networks, Washington, 1, pp. 565-568, 1990. • 1990

Similar Papers

Loading similar papers…