If we include to Linear Discriminant Analysis quadratic parameters we get Quadratic Discriminant Analysis classifier. Number of parameters is $(K-1)\times[(p\times(p+3)/2) + 1]$ where K is number of classes and p is number of features.

Why $K-1$? In the book it is said that we only need to compare $\delta_{k}(x) - \delta_{K}(x)$ of discriminant functions of some prespecified class K, but why do we do that and how it works?

$(p\times(p+3)/2) + 1$ is number of factors in multivariate quadratic function how is it calculated?


Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.