News for hackers. Stuff that matters.
Re:The main trick in machine learning by khawkins on Monday December 09, 2013 @08:22PM (#6878373)
I would say, to be succinct, that the main trick in ML is Occam's Razor (http://en.wikipedia.org/wiki/Occam%27s_razor).

It has been found that, for most problems, a simple model which well represents previous experience should be accepted instead of a more complex one with marginally better representation. I would claim that the reason this generally works is an empirical discovery, as opposed to a mathematical result, but probably has philosophical implications in its success.

Re:The main trick in machine learning by JASchilz on Monday December 09, 2013 @08:31PM (#6878406)
Check out Bayesian Model Selection. It's the mathematical expression of Occam's Razor.
Re:The main trick in machine learning by khawkins on Monday December 09, 2013 @10:46PM (#6878868)
My point is that it shows up everywhere, just in different forms. Sparse coding has a penalty for large basises. Gaussian process regression tunes the density of its representation using Bayesian model Selection. SVMs have a slack parameter which dictates how many errors you'll tolerate to reduce the number of hyperplanes.
Re:The main trick in machine learning by JASchilz on Monday December 09, 2013 @11:20PM (#6878951)
I apologize, my reply was aimed too low.
Re:The main trick in machine learning by PeterisP on Wednesday December 11, 2013 @10:21AM (#6888005)
This is often represented explicitly within the model math by adding a penalty factor that marks more complex models as worse and thus also optimizes simplicity in addition to accuracy.