today blodgett read instructive article, its english so cute!
excerpt for you here from abstract:
“Most of them, however, are redundant or irrelevant, and their existence may straightly lead to poor performance of learning algorithms. Hence, it is a compelling requisition for their practical applications to choose most salient features.”
straightly! :D blodgett thinks it hasn’t read this outside of austen.
cannot find good free copy (this seems best but may be temporary: http://74.125.155.132/scholar?q=cache:XoEXJND40KkJ:scholar.google.com)
other favourite part:
“Unfortunately, no systematic study has been conducted on the reliability and effectiveness of these [technique]s and the multitudinous algorithms will bewilder practitioners.”
ohnoes! the poor bewildered practitioners :(
plus bonus points for casual reference to miners! read all about it eh