multi assignment clustering of Boolean data 2.001

Mario Frank, Andreas P. Streich — Sat, 03 Mar 2012 09:04:04 -0000

The program takes a binary matrix as an input and factorizes it into two binary matrices such that their Boolean matrix product is an approximation of the input matrix.

The optimization uses an annealed EM scheme to maximize the likelihood of the latent feature model described in our paper.

Originally, we developed our model and code to solve the role mining problem from the field of information theory. However, it could be used to approximately factorize any binary matrix. This is useful for database tiling, the set basis problem, market basket analysis and other problems.

Please contact us if you have comments or questions.

Comment by Mario Frank on 2011-08-17 16:20

Mario Frank — Wed, 17 Aug 2011 16:20:00 -0000

hello world

Comment by Mario Frank on 2011-08-17 16:26

Mario Frank — Wed, 17 Aug 2011 16:26:25 -0000

text polished a bit

mloss.org multi assignment clustering of Boolean data

multi assignment clustering of Boolean data 2.001

Comment by Mario Frank on 2011-08-17 16:20

Comment by Mario Frank on 2011-08-17 16:26