Learning neural networks with noisy inputs using the errors-in-variables approach

@article{Gorp2000LearningNN,
  title={Learning neural networks with noisy inputs using the errors-in-variables approach},
  author={J{\"u}rgen Van Gorp and Johan Schoukens and Rik Pintelon},
  journal={IEEE transactions on neural networks},
  year={2000},
  volume={11 2},
  pages={402-14}
}
Currently, most learning algorithms for neural-network modeling are based on the output error approach, using a least squares cost function. This method provides good results when the network is trained with noisy output data and known inputs. Special care must be taken, however, when training the network with noisy input data, or when both inputs and outputs contain noise. This paper proposes a novel cost function for learning NN with noisy inputs, based on the errors-in-variables stochastic… CONTINUE READING

Similar Papers

Loading similar papers…