Using sequentialfs to maximise mutual information for feature selection

2 visualizaciones (últimos 30 días)
Newman el 8 de Oct. de 2016
Editada: Newman el 8 de Oct. de 2016
I want to maximise mutual information (objective function)
As you can see this is the function which I want to maximise .Where x is a feature vector and y is a class label.How do I write a function that maximises it and then uses sequentialffs to search along all the subsets of the feature vector that has to be used for classification.

Respuestas (0)


Más información sobre Statistics and Machine Learning Toolbox en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by