pooling layer

scroll ↓ to Resources

Note

  • convolutional neural network produces higher weights when it did find some pattern. We are interested in highlighting this fact, not the fact that it didn’t find anything in a given region. That’s why either max pooling or average pooling is applied
  • doesn’t have trainable parameters

Resources


table file.inlinks, filter(file.outlinks, (x) => !contains(string(x), ".jpg") AND !contains(string(x), ".pdf") AND !contains(string(x), ".png")) as "Outlinks" from [[]] and !outgoing([[]])  AND -"Changelog"