Top Network Posts
- 25Is there a plateau-shaped distribution?
- 19When to use in-place layers in Caffe?
- 13Auto-encoders with tied weights in Caffe
- 12Why are neural networks easily fooled?
- 12Cross-Entropy or Log Likelihood in Output layer
- 7What's the difference between momentum based gradient descent, and Nesterov's accelerated gradient descent?
- 7Different definitions of the cross entropy loss function
- View more network posts →