[R] Strange question/result about SVM

Steve Lianoglou mailinglist.honeypot at gmail.com
Mon Sep 14 22:37:17 CEST 2009


> 	(Although I must admit that the current thread about SVMs leaves
> 	me --- personally --- cold.  I think that SVMs are a load of dingos'
> 	kidneys.

So, you're saying that you find them so essential that life w/o them  
is practically impossible ... unless we have dingo dialysis machines  
now? Or worse .. dingo's should go extinct?

>  As I may have said on this list previously, I think
> 	fortune("machine learning") is relevant.)

Not sure that that's entirely true, but who needs models and  
assumptions when you can get your hands on some objective function to  
optimize, anyway?

While not exactly relevant, I've been a big fan of this Vapnik photo ...

http://aboutintelligence.blogspot.com/2009/01/vapniks-picture-explained.html

My $.2 worth of levity,

-steve

ps - You can put a smiley at the end of each sentence, but then it  
just seems to look like line noise ... infer them as you see fit ...

--
Steve Lianoglou
Graduate Student: Computational Systems Biology
   |  Memorial Sloan-Kettering Cancer Center
   |  Weill Medical College of Cornell University
Contact Info: http://cbio.mskcc.org/~lianos/contact




More information about the R-help mailing list