Reducing the Dimensionality of Data with Neural Networks

Title: Reducing the Dimensionality of Data with Neural Networks
Authors: G. E. Hinton, R. R. Salakhutdinov
Published: 2006-07-28
Link: https://www.science.org/doi/10.1126/science.1127647

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.

---