Akaike’s Information Criterion for Linearly Separable Clusters

Using the Akaike Information Criterion (AIC) in cluster analysis with linearly separable components, the paper demonstrates the superiority of using the vector of slopes as inputs to the K-Means algorithm over using the raw data in determining the number of clusters.

 

Keywords - AIC(Akaike’s Information Criterion), Kullback-Leibler information, cluster analysis, linear separability