On the initialization and optimization of multilayer perceptrons

  title={On the initialization and optimization of multilayer perceptrons},
  author={Nico Weymaere and Jean-Pierre Martens},
  journal={IEEE transactions on neural networks},
  volume={5 5},
Multilayer perceptrons are now widely used for pattern recognition, although the training remains a time consuming procedure often converging toward a local optimum. Moreover, as the optimum network size and topology are usually unknown, the search of this optimum requires a lot of networks to be trained. In this paper the authors propose a method for properly initializing the parameters (weights) of a two-layer perceptron, and for identifying (without the need for any error-backpropagation… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 26 extracted citations

Similar Papers

Loading similar papers…