1 Matching Annotations
  1. Oct 2015
  2. cs231n.github.io cs231n.github.io
    CS231n Convolutional Neural Networks for Visual Recognition
    1
    1. chintak 14 Oct 2015
      full loss function as coming from a Gaussian prior over the weight matrix WW, where instead of MLE we are performing the Maximum a posteriori (MAP) estimation. We mention these interpretations to help your intuitions, but the full details of this derivation are beyond the scope of this class.

      Can anyone provide resources where I can find this derivation? In particular, the derivation for the regularization term \(R(W)\) coming from a Gaussian prior on \(W\).

      resource map mle details
    Visit annotations in context

    Tags

    Annotators

    URL

    cs231n.github.io/linear-classify/