Basically, one hidden layer networks are already universal approximator; however, it's a nonconstructive result. This article is semi-constructive, - they train more complicated model, then emulate it with a simpler model, but do not know how to train the simple model directly.
Basically, one hidden layer networks are already universal approximator; however, it's a nonconstructive result. This article is semi-constructive, - they train more complicated model, then emulate it with a simpler model, but do not know how to train the simple model directly.