Reducing the dimensionality of data with neural networks. (English) Zbl 1226.68083

Hinton, G. E.; Salakhutdinov, R. R.

Science 313, No. 5786, 504-507 (2006).

Summary: 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.

MSC:

68T05

Learning and adaptive systems in artificial intelligence

Software:

darch