News for hackers. Stuff that matters.

sivvy

Re:Use pew, not virtualenvwrapper, for Python virtualenvs on Friday September 08, 2017 @03:42PM (#15203353)
Why not use conda?
Re:Scientific research piracy site hit with $15M fine on Monday June 26, 2017 @02:03AM (#14634439)
...is $1.5M.
Re:An Introduction to Support Vector Machines on Thursday June 22, 2017 @05:19PM (#14615445)
Seems like in that case you would train both models separately on different cost functions. By phrasing it as a layer I was expecting both the SVM and the DNN could be trained simultaneously.
Re:An Introduction to Support Vector Machines on Thursday June 22, 2017 @03:49PM (#14614798)
Could you explain in a bit more detail how you would integrate an SVM layer into a DNN? The kernel matrix depends on all samples, while at training time you would only have access to those in the minibatch.
Re:Faster DOM on Thursday May 26, 2016 @04:25PM (#11781241)
I think he is actually a she.
The premise of the optimizations in this article don't always hold, unfortunately. If x is floating point, sum(reverse(x)) is unlikely to be equal to sum(x) for long enough x, and sorting x on beforehand will make this effect even more apparent.