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...
Paper Fields
Computer science
Materials science
Artificial intelligence
Programming language
Operating system
Algorithm
Nanotechnology
Layer (electronics)
Pattern recognition (psychology)
Artificial neural network
Principal (computer security)
Principal component analysis
Curse of dimensionality
Initialization
Gradient descent
Autoencoder
High dimensional
Paper Details
Title
Reducing the Dimensionality of Data with Neural Networks
DOI
Published Date
Jul 28, 2006
Journal
Volume
313
Issue
5786
Pages
504 - 507
Citation Distributions