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.
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)
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)