University of Cambridge > Talks.cam > Machine Learning Journal Club > Journal Club: "Reducing the Dimensionality of Data with Neural Networks"

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

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

Download to your calendar using vCal

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:

Note that ex-directory lists are not shown.

Other lists

Anthony Low Building (ALB), Clare Hall (main site), Herschel Road, Cambridge CB3 Cambridge Graphene Centre Seminar Room Faraday Institute for Science and Religion

Other talks

Title TBC Kirk Public Lecture: Title TBC Neutrality and The Atoll Verified Hypervisor Title TBC Tea and Coffee Break Climate, uncertainty, and the slippery measurement of Antarctic ice
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity