Supporting Online Material


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

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.