Code provided by Ruslan Salakhutdinov

Permission is granted for anyone to copy, use, modify, or distribute this program and accompanying programs and documents for any purpose, provided this copyright notice is retained and prominently displayed, along with a note saying that the original programs are available from our web page. The programs and documents are distributed without any warranty, express or implied. As the programs were written for research purposes only, they have not been tested to the degree that would be advisable in any important application. All use of these programs is entirely at the user's own risk.

How to make it work:

  1. Create a separate directory and download all these files into the same directory
  2. Download from the following 4 files:
    • train-images-idx3-ubyte.gz
    • train-labels-idx1-ubyte.gz
    • t10k-images-idx3-ubyte.gz
    • t10k-labels-idx1-ubyte.gz
  3. Unzip these 4 files by executing:
    • gunzip train-images-idx3-ubyte.gz
    • gunzip train-labels-idx1-ubyte.gz
    • gunzip t10k-images-idx3-ubyte.gz
    • gunzip t10k-labels-idx1-ubyte.gz
    If unzipping with WinZip, make sure the file names have not been changed by Winzip.
  4. Download AIS_RBM_Code.tar which contains 15 files OR
    download each of the following 15 files separately:
  5. For the toy experiment, run demo_toy in matlab.
  6. For running an AIS on the big RBM model, run demo_rbm in matlab.
  7. Make sure you have enough space to store the entire MNIST dataset on your disk.

This software is not fully optimized. If you find bugs, please e-mail me.

Contact Information

Ruslan Salakhutdinov
Department of Statistics, University of Toronto,
Email: rsalakhu [at] utstat [dot] toronto [dot] edu

Department of Statistics
University of Toronto
100 St. George Street, 6th floor
Toronto, Ontario M5S 3G3