Automatic sizing of neural networks for function approximation
- 1 October 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1062922X,p. 2005-2010
Abstract
Neural networks (NN) are a very efficient and powerful function approximation tool. Inspired by the brain structure and functions, NN are usually trained with backpropagation learning algorithm. A detailed benchmark on standard functions is provided, supporting in particular the automatic choice of the number of neurons in the hidden layer.Keywords
This publication has 4 references indexed in Scilit:
- Training feedforward networks with the Marquardt algorithmIEEE Transactions on Neural Networks, 1994
- Prediction Risk and Architecture Selection for Neural Networks1994
- Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer NetworksNeural Computation, 1993
- The Vapnik-Chervonenkis Dimension: Information versus Complexity in LearningNeural Computation, 1989