2014-02-28 15:42 GMT+01:00 Caleb <cloverev...@yahoo.com>: > I am training my SVM with the raw pixels value of the mnist dataset. > Just for fun, I round up all the pixel values to either 1 or 0, and this I > will call dataset1. Then I invert the 1 to 0 and 0 to 1 to form dataset2. > Thus dataset1 will consists of mainly zero and dataset2 mainly 1. > > I then train both of them using linear svm. The accuracies are similar, > for dataset1, 90.8%; dataset2, 90.0%. But the time taken to train dataset1 > is about 1 minute but to train dataset2 takes about 7 minutes. > > Is this just a one time quirk or maybe it is a well known fact that svm > trains faster with sparse data?
LinearSVC will convert to Liblinear's custom sparse format internally, so it's no surprise that it's faster with many zeros. ------------------------------------------------------------------------------ Flow-based real-time traffic analytics software. Cisco certified tool. Monitor traffic, SLAs, QoS, Medianet, WAAS etc. with NetFlow Analyzer Customize your own dashboards, set traffic alerts and generate reports. Network behavioral analysis & security monitoring. All-in-one tool. http://pubads.g.doubleclick.net/gampad/clk?id=126839071&iu=/4140/ostg.clktrk _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
