TY - JOUR
T1 - Reducing the Dimensionality of Data with Neural Networks
JF - Science
JO - Science
SP - 504
LP - 507
M3 - 10.1126/science.1127647
VL - 313
IS - 5786
AU - Hinton, G. E.
AU - Salakhutdinov, R. R.
Y1 - 2006/07/28
UR - http://science.sciencemag.org/content/313/5786/504.abstract
N2 - 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.
ER -