News for hackers. Stuff that matters.
Re:Machine learning works spectacularly well, but mathematic... by vidarh on Friday December 04, 2015 @11:10AM (#10677099)
Very, very roughly a neural network consists of a bunch of connected nodes that you propagate signals through. Each of those connections carries a weight that affects how the signal gets propagated through the rest of the network.

Let's say a specific problem has only one very specific set of connections that matters. You'll eventually add up with weights that reflects that, but that doesn't prevent a lot of other connections from having weights set during training, but that may end up being cancelled out or reduced enough to have no meaningful impact whatsoever on the end result.

Re:Machine learning works spectacularly well, but mathematic... by aswanson on Friday December 04, 2015 @03:33PM (#10678944)
Is that why sparsity terms have been introduced into objective functions?