Self-Organising Map (SOM) with Principle Component Analysis (PCA)

Dear all, I want to use Self-Organising Map (SOM) [unsupervised machine learning] for my anomaly detection problem. But before that I would like to find suitable input features that cause the best results. I have total of eight input features. Would you use Principle Component Analysis (PCA) to find best features? What would you do? Regards, Naghmeh

Answer 1

[Greg Heath]

It is not clear if you have a well defined output.

If so, it IS NOT the variation of the inputs that are paramount.

It IS the variation of the outputs w.r.t. the inputs.

Check out principal COORDINATE analysis (very different from principal COMPONENT analysis!)

Hope that helps.

Thank you for formally accepting my answer

Greg