Machine learning Posted on 3 December 2008 by John Brendan O’Connor has a thoughtful comparison of machine learning and statistics this morning.
3 thoughts on “Machine learning”
The main difference is that statistics was designed for an age where having 30 samples was a lot. Machine Learning copes with millions of samples. I do multidimensional analysis (OLAP) and deal with billions of samples.
Guess who is on top of the food chain! Me! ;-)
One of the fortune cookies in R (package ‘fortunes’, fortune 50) has this quote:
To paraphrase provocatively, ‘machine learning is statistics minus any checking of models and assumptions’.
– Brian D. Ripley (about the difference between machine learning and statistics)
useR! 2004, Vienna (May 2004)