Journal Club: "Reducing the Dimensionality of Data with Neural Networks"

Add to your list(s) Download to your calendar using vCal

• O. Stegle
• Friday 08 December 2006, 12:30-13:30
• TCM Seminar Room, Cavendish Laboratory, Department of Physics.

If you have a question about this talk, please contact Oliver Stegle.

G. E. Hinton* and R. R. Salakhutdinov High-dimensional data can be converted to low-dimensional codes by training a multilayer 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 the initial weights are close to a good solution. We describe an effective way of initializing 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. —— http://www.sciencemag.org/cgi/reprint/313/5786/504.pdf

please also look at supporting online Material:

http://www.sciencemag.org/cgi/data/313/5786/504/DC1/1

This talk is part of the Machine Learning Journal Club series.

This talk is included in these lists:

• Cambridge talks
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Interested Talks
• ML
• Machine Learning Journal Club
• Machine Learning Summary
• Quantum Matter Journal Club
• TCM Seminar Room, Cavendish Laboratory, Department of Physics
• TQS Journal Clubs
• rp587
• yk373's list

Note that ex-directory lists are not shown.