Re:Using neural nets to recognize handwritten digits
by shoo on Tuesday November 26, 2013 @12:26AM
(#6799327)
Yes.
I'd go further - the "nice fitting algorithm" is to minimise the error on the training set as a function of the weight parameters, and one obvious way to (locally) minimise that is gradient descent + the chain rule.
The math / applied math machinery is all incredibly general, and a useful way to think about many machine learning algorithms.
http://en.wikipedia.org/wiki/Gradient_descent http://en.wikipedia.org/wiki/Chain_rule#Higher_dimensions
Not to say that applied math is the only valuable perspective to think about, there's clearly also statistical and computational views as well. E.g. we're trying to approximate a function that we can never directly evaluate (error on the samples we havent seen yet)
Re:Using neural nets to recognize handwritten digits
by fpgaminer on Monday November 25, 2013 @09:09PM
(#6798615)
I believe svantana was merely trying to differentiate ANNs from magic, not ANNs from other ML algorithms. Indeed you are correct that machine learning as a whole could be seen as function fitting.
Couldn't "function approximator" describe most machine learning approaches? And a nice fitting algorithm is of course the goal.