Advices about reading/presenting/writing papers:

  1. How to Get Your SIGGRAPH Paper Rejected, Jim Kajiya, SIGGRAPH 1993 Papers Chair. [link]
  2. "How to Read a Research Paper" by Spencer Rugaber. [link]
  3. "How to Present a Paper" by Ashwin Ram. [link]
  4. "You and Your Research," Dr. Richard W. Hamming, March 7, 1986. [link]
  5. Prof. David Patterson's talks on career in research and academia. [link]
  6. Gatech research resources here

Matlab:

Matlab is recommended for programming and demonstration in this class although use of other languages like Java or C++ is also welcome. The easiest place to use Matlab is in one of the CUIT-administered computer labs. Perhaps the most convienent lab, for both location and operating hours, is the CUIT Engineering Terrace (251 Mudd second floor) lab where all workstations are installed with Matlab and several other software suites you might need. Additionally, if you wish to work from home, you can run Matlab via a unix shell by logging into the CUNIX computer cluster by using "ssh UNI@cunix.cc.columbia.edu" and then run 'matlab'. The program resides on /opt/local/bin/matlab'.

You can also buy a "student edition" of Matlab from the Mathworks. You will need Image Processing Toolbox and Statistics Toolbox in order to use many pre-defined functions. Make sure to check the version numbers of the software when searching for specific functions.

Software:

  1. Tutorials on Matlab
    1. Mathwork's series of tutorials for beginners to advanced users, code and graphical demos [link]
    2. Mathworks' Matlab documentation [link]
    3. Introducing Matlab [link]
    4. A demo of image processing in Matlab [link]
    5. Various Matlab tutorial and introductions [UNH, MTU, etc, etc]
  2. Machine Learning Software
    1. Kevin Murphy's Bayesian Network Toolbox and Machine Learning software page [link]
    2. Netlab by Bishop and Nabney [link]
    3. Bayesian Network Editor and Toolkit by Microsoft [link]
    4. LIBSVM: a library for support vector machines, by Chih-Chung Chang and Chih-Jen Lin [link]
    5. Kernel machines resrouce site, the portal of SVM [link]
    6. Graphic Model ToolKit by Jeff Bilmes and Geoffrey Zweig [link]

Other Useful Resources:

  1. Prof. William Freeman's class on "Learning and Inferencing of Vision" [link] offered at MIT. Our class is modeled after the above one, with a different focus on video analysis/indexing. A list of papers and student presentations in Prof. Freeman's class is here. It includes examples of excellent presentations and computer examples.
  2. How to create your web site in CUNIX?
    see instructions at: http://www.columbia.edu/acis/webdev/create.html