Multilayer Perceptron Trained with Numerical Gradient

  title={Multilayer Perceptron Trained with Numerical Gradient},
  author={Włodzisław Duch and Mirosław Kordos},
of MLP networks is presented. Several versions of the algorithm and the influence of various parameters on the training process are discussed. Optimization of network parameters based on global search with numerical gradient is presented. Examples of two-dimensional projection of the error surface are shown and the influence of various numerical gradient parameters on the error surface is presented. The speed and accuracy of this method is compared with the search-based MLP training algorithm. 

From This Paper

Figures, tables, and topics from this paper.

Similar Papers

Loading similar papers…