Hypothesis

2 Matching Annotations

Jan 2015
cs231n.github.io cs231n.github.io

CS231n Convolutional Neural Networks for Visual Recognition

1
1. alshedivat 11 Jan 2015
  
  in Public
  
  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)?
  
  optimization
Visit annotations in context

Tags

optimization

Annotators

alshedivat

URL

cs231n.github.io/optimization-1/
cs231n.github.io cs231n.github.io

CS231n Convolutional Neural Networks for Visual Recognition

1
1. alshedivat 11 Jan 2015
  
  in Public
  
  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."
  
  k-NN probabilistic model
Visit annotations in context

Tags

k-NN

probabilistic model

Annotators

alshedivat

URL

cs231n.github.io/classification/