%0 Journal Article
%A Hinton, G. E.
%A Salakhutdinov, R. R.
%T Reducing the Dimensionality of Data with Neural Networks
%D 2006
%R 10.1126/science.1127647
%J Science
%P 504-507
%V 313
%N 5786
%X High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such “autoencoder” networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.
%U https://science.sciencemag.org/content/sci/313/5786/504.full.pdf