hello everyone. I am currently working with genetic algorithms, and I need to get a fitness function, using the fisher score. The fisher score is used for clustering, and classifying individuals. I don't know how it works completely, but the general idea is that it generates a vector which separates classes, thus classifying them not depending on a multidimensional calculation. As for my case, i am working with a set of data, each one having 50 atributes and one class, and I have to use this information to get the fisher score and make a function known as 'JFunction' to classify my initially random generated set of data, to find out the 10 best classifiers.
Now, if anyone knows how the fisher score works, that's a plus. But my real question is in how to work matrix in C#. I need to get transpose matrix, covariance and variance, and other simple matrix operations.
Edited by petocities, 24 November 2008 - 04:28 PM.