7 votes

Are Deep Neural Networks Dramatically Overfitted?

2 comments

  1. skybrian
    Link
    Apparently most layers in deep learning networks aren't actually used. From the article: "The lottery ticket hypothesis states that a randomly initialized, dense, feed-forward network contains a...

    Apparently most layers in deep learning networks aren't actually used. From the article: "The lottery ticket hypothesis states that a randomly initialized, dense, feed-forward network contains a pool of subnetworks and among them only a subset are 'winning tickets' which can achieve the optimal performance when trained in isolation."

    This seems to explain why the networks can easily be pruned after training is done. There's a lot of data that's left over from failed attempts.

    3 votes
  2. Staross
    Link
    Very interesting, thanks.

    Very interesting, thanks.