Note to users. If you're seeing this message, it means that your browser cannot find this page's style/presentation instructions -- or possibly that you are using a browser that does not support current Web standards. Find out more about why this message is appearing, and what you can do to make your experience of our site the best it can be.

Science 28 July 2006:
Vol. 313. no. 5786, pp. 504 - 507
DOI: 10.1126/science.1127647


Reducing the Dimensionality of Data with Neural Networks
G. E. Hinton and R. R. Salakhutdinov

Supporting Online Material

This supplement contains:
Materials and Methods
Figs. S1 to S5
Matlab Code

Download supplement

This file is in Adobe Acrobat PDF format.

Computer codes. Nine ASCII files containing Matlab codes for learning autoencoders, packaged as a zipped Unix tarfile. Users should download the compressed file to their machine and extract them on their local hard drive, using the instructions below):

Instructions for downloading and decompressing files:

  1. Create a temporary folder on your machine's hard drive.
  2. Save each compressed archive to the temporary folder you created, using the links above.
  3. Expand the compressed file in the temporary folder using decompression software such as WinZip (Windows; www.winzip.com) or StuffIt Expander (Windows and Mac; www.stuffit.com). The result will be a Unix "tape archive" file, or tarfile. Use the same programs to extract the data files from the tarfile. Users in Unix environments can also use standard Unix command-line tools to extract the files.
  4. README.txt file provides instructions for executing these scripts in Matlab.

Return to article

To Advertise     Find Products

Science. ISSN 0036-8075 (print), 1095-9203 (online)