RT Journal Article
SR Electronic
T1 Reducing the Dimensionality of Data with Neural Networks
JF Science
JO Science
FD American Association for the Advancement of Science
SP 504
OP 507
DO 10.1126/science.1127647
VO 313
IS 5786
A1 Hinton, G. E.
A1 Salakhutdinov, R. R.
YR 2006
UL http://science.sciencemag.org/content/313/5786/504.abstract
AB 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.