Le 11 avril 2012 00:28, Michael Selik <[email protected]> a écrit : > Hello, > > As per the docs' suggestion to ask around before starting my own work: is > anyone working on a weighted mean shift implementation? > > The purpose of this is to account for some observations being more reliable > than others. Or perhaps I've misunderstood the current implementation and it > already allows for this?
I don't think so but you should really start from the existing implementation to extend it when needed rather roll a whole new implementation from scratch. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ Better than sec? Nothing is better than sec when it comes to monitoring Big Data applications. Try Boundary one-second resolution app monitoring today. Free. http://p.sf.net/sfu/Boundary-dev2dev _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
