Taking on the Curse of Dimensionality in Joint Distributions Using Neural Networks

Taking on the Curse of Dimensionality in Joint Distributions Using Neural Networks (2000)

by Samy Bengio , Yoshua Bengio

Venue:	IEEE Transactions on Neural Networks, special issue on Data Mining and Knowledge Discovery
Citations:	10 - 4 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Taking on the Curse of Dimensionality in Joint Distributions Using Neural Networks	user correction - Legacy Corrections
AUTHOR NAME	Samy Bengio	SVM HeaderParse 0.1
AUTHOR NAME	Yoshua Bengio	SVM HeaderParse 0.1
ABSTRACT	\|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 multi-layer neural network to represent the joint distribution of the variables as the product of conditional distributions. The neural network can be interpreted as a graphical model without hidden random variables, but in which the conditional distributions are tied through the hidden units. The connectivity of the neural network can be pruned by using dependency tests between the variables (thus reducing signicantly the number of parameters). Experiments on modeling the distribution of several discrete data sets show statistically signicant improvements over other methods such as naive Bayes and comparable Bayesian networks,...	user correction - Legacy Corrections
YEAR	2000	INFERENCE
VENUE	IEEE Transactions on Neural Networks, special issue on Data Mining and Knowledge Discovery	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
PAGES	200--0	INFERENCE
VOLUME	11	INFERENCE
CITATIONS	14 found	ParsCit 1.0