Report

Reducing the Dimensionality of Data with Neural Networks

Science  28 Jul 2006:
Vol. 313, Issue 5786, pp. 504-507
DOI: 10.1126/science.1127647

You are currently viewing the abstract.

View Full Text

Abstract

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.

View Full Text

Cited By...