2 Matching Annotations
  1. Jan 2015
    1. There are other ways of performing the optimization (e.g. LBFGS), but Gradient Descent is currently by far the most common and established way of optimizing Neural Network loss functions.

      Are there any studies that compare different pros and cons of the optimization procedures with respect to some specific NN architectures (e.g., classical LeNets)?

    1. k - Nearest Neighbor Classifier

      Is there a probabilistic interpretation of k-NN? Say, something like "k-NN is equivalent to [a probabilistic model] under the following conditions on the data and the k."