Daniel@0: Daniel@0: Bayes Net Toolbox for Matlab Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Bayes Net Toolbox for Matlab

Daniel@0: Written by Kevin Murphy, 1997--2002. Daniel@0: Last updated: 19 October 2007. Daniel@0: Daniel@0:

Daniel@0: Daniel@0: Daniel@0:
Daniel@0: Matlab logo Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0:
Daniel@0: Click to subscribe to the BNT email list
Daniel@0:
Daniel@0: ( Daniel@0: http://groups.yahoo.com/group/BayesNetToolbox) Daniel@0: Daniel@0:
Daniel@0: Daniel@0: Daniel@0:

Daniel@0:

Daniel@0:

Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Major features

Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Supported probabilistic models

Daniel@0:

Daniel@0: It is trivial to implement all of Daniel@0: the following probabilistic models using the toolbox. Daniel@0:

Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Why do I give the code away?

Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Why Matlab?

Daniel@0: Daniel@0: Matlab is an interactive, matrix-oriented programming language that Daniel@0: enables one to express one's (mathematical) ideas very concisely and directly, Daniel@0: without having to worry about annoying details like memory allocation Daniel@0: or type checking. This considerably reduces development time and Daniel@0: keeps code short, readable and fully portable. Daniel@0: Matlab has excellent built-in support for many data analysis and Daniel@0: visualization routines. In addition, there are many useful toolboxes, e.g., for Daniel@0: neural networks, signal and image processing. Daniel@0: The main disadvantages of Matlab are that it can be slow (which is why Daniel@0: we are currently rewriting parts of BNT in C), and that the commercial Daniel@0: license is expensive (although the student version is only $100 in the US). Daniel@0:

Daniel@0: Many people ask me why I did not use Daniel@0: Octave, Daniel@0: an open-source Matlab clone. Daniel@0: The reason is that Daniel@0: Octave does not support multi-dimensional arrays, Daniel@0: cell arrays, objects, etc. Daniel@0:

Daniel@0: Click here for a more detailed Daniel@0: comparison of matlab and other languages. Daniel@0: Daniel@0: Daniel@0: Daniel@0:

Acknowledgments

Daniel@0: Daniel@0: I would like to thank numerous people for bug fixes, including: Daniel@0: Rainer Deventer, Michael Robert James, Philippe Leray, Pedrito Maynard-Reid II, Andrew Ng, Daniel@0: Ron Parr, Ilya Shpitser, Xuejing Sun, Ursula Sondhauss. Daniel@0:

Daniel@0: I would like to thank the following people for contributing code: Daniel@0: Pierpaolo Brutti, Ali Taylan Cemgil, Tamar Kushnir, Daniel@0: Tom Murray, Daniel@0: Nicholas Saunier, Daniel@0: Ken Shan, Daniel@0: Yair Weiss, Daniel@0: Bob Welch, Daniel@0: Ron Zohar. Daniel@0:

Daniel@0: The following Intel employees have also contributed code: Daniel@0: Qian Diao, Shan Huang, Yimin Zhang and especially Wei Hu. Daniel@0: Daniel@0:

Daniel@0: I would like to thank Stuart Russell for funding me over the years as Daniel@0: I developed BNT, and Gary Bradksi for hiring me as an intern at Intel, Daniel@0: which has supported much of the recent developments of BNT. Daniel@0: Daniel@0: Daniel@0: Daniel@0: