Reducing the Dimensionality of Data with Neural Networks
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.
- Publication:
-
Science
- Pub Date:
- July 2006
- DOI:
- 10.1126/science.1127647
- Bibcode:
- 2006Sci...313..504H
- Keywords:
-
- COMP/MATH