Reducing the Dimensionality of Data with Neural Networks

American Association for the Advancement of Science (AAAS) - Tập 313 Số 5786 - Trang 504-507 - 2006
Geoffrey E. Hinton1, Ruslan Salakhutdinov1
1Department of Computer Science, University of Toronto, 6 King's College Road, Toronto, Ontario M5S 3G4, Canada.

Tóm tắt

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.

Từ khóa


Tài liệu tham khảo

10.1016/0885-2308(87)90026-X

D. DeMers, G. Cottrell, Advances in Neural Information Processing Systems 5 (Morgan Kaufmann, San Mateo, CA, 1993), pp. 580–587.

10.1126/science.269.5232.1860

10.1162/neco.1997.9.7.1493

P. Smolensky, Parallel Distributed Processing: Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland, Eds. (MIT Press, Cambridge, 1986), pp. 194–281.

G. E. Hinton, Neural Comput.14, 1711 (2002).

10.1073/pnas.79.8.2554

See supporting material on Science Online.

10.1162/neco.2006.18.7.1527

M. Welling, M. Rosen-Zvi, G. Hinton, Advances in Neural Information Processing Systems 17 (MIT Press, Cambridge, MA, 2005), pp. 1481–1488.

The MNIST data set is available at http://yann.lecun.com/exdb/mnist/index.html.

The Olivetti face data set is available at www.cs.toronto.edu/roweis/data.html.

The Reuter Corpus Volume 2 is available at http://trec.nist.gov/data/reuters/reuters.html.

10.1002/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9

10.1126/science.290.5500.2323

10.1126/science.290.5500.2319

We thank D. Rumelhart M. Welling S. Osindero and S. Roweis for helpful discussions and the Natural Sciences and Engineering Research Council of Canada for funding. G.E.H. is a fellow of the Canadian Institute for Advanced Research.