Taking on the curse of dimensionality in joint distributions using neural networks

@article{Bengio2000TakingOT,
  title={Taking on the curse of dimensionality in joint distributions using neural networks},
  author={Samy Bengio and Yoshua Bengio},
  journal={IEEE transactions on neural networks},
  year={2000},
  volume={11 3},
  pages={
          550-7
        }
}
The curse of dimensionality is severe when modeling high-dimensional discrete data: the number of possible combinations of the variables explodes exponentially. In this paper, we propose a new architecture for modeling high-dimensional data that requires resources (parameters and computations) that grow at most as the square of the number of variables, using a multilayer neural network to represent the joint distribution of the variables as the product of conditional distributions. The neural… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 33 CITATIONS

Similar Papers

Loading similar papers…